Dissertations / Theses on the topic 'Integration and transfer learning'
To see the other types of publications on this topic, follow the link: Integration and transfer learning.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Integration and transfer learning.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Brenner, Aimee Michelle. "Investigating the Practices in Teacher Education that Promote and Inhibit Technology Integration in Early Career Teachers." Diss., Virginia Tech, 2012. http://hdl.handle.net/10919/39472.
Full textAbstract:
In an attempt to promote the transfer of technology integration knowledge and skills in preservice teachers, studies have attempted to identify effective instructional technology integration practices on the part of the teacher education program, as well as exemplary programs themselves (Hofer, 2005; Mergendoller et al., 1994; Strudler & Wetzler, 1999). A significant number of studies focus on examining various components of technology integration plans within teacher education programs, but few have extended this examination to determine if transfer is evidenced in the practices of graduates. The purpose of this study, therefore, was to identify instructional technology integration strategies and practices in preservice teacher education that contribute to the transfer of technology integration knowledge and skills to the instructional practices of early career teachers.
This study employed a two-phase, sequential explanatory strategy, where quantitative data were collected via an online survey during the first phase and then interview data were collected during the second phase. The targeted sample population for this research study consisted of male and female early career teachers who had completed a graduate level teacher education program through the School of Education (SOE) at a large, research university located in the Southeast. Overall, these early career teachers assessed themselves as being proficient users of instructional technologies and feeling comfortable with their level of technology integration in the classroom. Out of nine qualities demonstrated in literature to promote learning transfer of technology integration knowledge and skills, the early career teachers reported the top three factors found in the study institution to be: the modeling of effective uses of technology integration by faculty in content-specific areas; opportunities to reflect upon technology integration practices in the classroom; and opportunities to practice and experiment with instructional technologies.
The early career teachers reported the three top barriers inhibiting technology integration in their classrooms as being: too much content to cover; lack of time to design and implement technology-enhanced lessons; and a lack of software resources. Although a majority of the early career teachers reported that the teacher education program overall prepared them to integrate technology into the classroom, they also reported that opportunities to practice technology integration and having access to expert guidance during their field experiences were lacking. Several suggestions were made by study respondents and these included: providing more opportunities to experiment and play with instructional technologies like SmartBoards; faculty support with regards to implementing and practicing with technology integration in field experiences; and technology courses that focus on up-to-date instructional technology tools within each of the content areas.
Findings from this study might be useful to teacher educators and researchers because it provides naturalistic recommendations (Stake, 1995) on how to improve their programs that are corroborated by the literature, and it offers an adapted survey that can be utilized to investigate technology integration transfer from the teacher education period to the early classroom practice period of new teachers.Ph. D.
2
Glaister, Karen. "Learning and transfer of dosage calculations: An evaluation of integrative and computerised instructional approaches." Thesis, Glaister, Karen (1998) Learning and transfer of dosage calculations: An evaluation of integrative and computerised instructional approaches. Masters by Research thesis, Murdoch University, 1998. https://researchrepository.murdoch.edu.au/id/eprint/52195/.
Full textAbstract:
Dosage calculations are an essential skill for current nurse practitioners. The challenge for educators is to determine how the learner can be best assisted to learn and apply both general and specific knowledge and skills. This fundamental issue of providing instruction that is meaningful and able to be utilised in another setting is an age-old concern. It can be seen from the posology literature that outcomes from a diversity of instructional attempts have generally been limited.
This exploratory field study investigated the effect of specifically prepared instructional approaches upon learning outcome and also the learners' ability to transfer this knowledge. The research is grounded in both transfer of learning and metacognitive-regulatory theory. Three instructional approaches were developed and considered in this study. The computerised learning approach was designed to encourage the low-road of learning providing for automaticity in skill performance. The integrative learning approach incorporated process-oriented instruction to support high-road learning and also repetitive practice to foster the low-road of learning. In addition, it included small group discussion to address the affective component of mathematical phobia often intrinsic to dosage calculations. The third approach combined the strategies provided in both the computerised and integrative learning approaches.
Based upon the literature, it was assumed that the integrative approach would be most effective in developing all forms of knowledge, particularly conditional knowledge, and consequently greater performance in far transfer tasks would be evidenced. Furthermore, this effect would be greatest in those learners who reported a negative attitude towards mathematics and mathematical testing and who also lacked self-regulation or external-regulation of learning. The combination of the computerised and integrative approach was expected to enhance the low-road of learning and consequently greater performance on near transfer tasks would be evidenced.
Evaluation used a methodological mix of both quantitative and qualitative approaches. The findings were not entirely conclusive, although they did offer some support to the study claims and interesting insight into other issues that need to be accounted for in exploratory field studies of this type.
Overall, it appeared that computerised learning might have been more influential in the development of procedural knowledge. However, when learners reported higher levels of negative attitudes towards mathematics and mathematical testing the integrative approach was more effective than the computerised approach in developing procedural knowledge. There was some evidence to suggest that when the learner reported being highly self-regulated or reliant on external-regulation, procedural knowledge development was interfered with when they received the combination of computerised and integrative learning. Although not statistically proven the integrative approach did result in higher scores on conditional knowledge measures in both the first and second post-tests. However when the effect of negative attitudes towards mathematics and mathematical testing was accounted for, then statistical support was evident, indicating that the integrative approach was more effective than the computerised approach under these circumstances. This effect was also noted when the learner reported a medium level of self-regulation. Generally the reported level of metacognitive-regulation did not appear to influence the treatment effects. None of the treatments examined demonstrated greater effectiveness on measures of far transfer.
These results support the findings of earlier studies both within the posology and transfer of learning literature asserting that the phenomenon of transfer can be elusive and does not naturally ensue from attempts made to improve upon instructional approaches. However due to institutional constraints the intervention period in the present study was markedly short affecting the integrity of the conceptual framework underlying the study. Despite this, the statistical evidence from the study suggests that both the integrative and computerised learning approach are worthy inclusions into future instructional approaches aimed towards developing competency in dosage calculations.
3
Chapman, Shelley Ann. "A Theory of Curriculum Development in the Professions: An Integration of Mezirow's Transformative Learning Theory with Schwab's Deliberative Curriculum Theory." [Yellow Springs, Ohio] : Antioch University, 2007. http://rave.ohiolink.edu/etdc/view?acc_num=antioch1173793131.
Full textAbstract:
Thesis (Ph. D.)--Antioch University, 2007.Title from PDF t.p. (viewed Apr. 10, 2007). Advisor: Jon F. Wergin. Keywords: transformative learning theory, deliberative curriculum theory, graduate professional education, theory building, higher education. Includes bibliographical references (p. 377-399).
4
Katzenbach, Michael. "Individual Approaches in Rich Learning Situations Material-based Learning with Pinboards." Saechsische Landesbibliothek- Staats- und Universitaetsbibliothek Dresden, 2012. http://nbn-resolving.de/urn:nbn:de:bsz:14-qucosa-80328.
Full textAbstract:
Active Approaches provide chances for individual, comprehension-oriented learning and can facilitate the acquirement of general mathematical competencies. Using the example of pinboards, which were developed for different areas of the secondary level, workshop participants experience, discuss and further develop learning tasks, which can be used for free activities, for material based concept
formation, for coping with heterogeneity, for intelligent exercises, as tool for the presentation of students’ work and as basis for games. The material also allows some continuous movements and can thus prepare an insightful usage of dynamic geometry programs. Central Part of the workshop is a work-sharing group work with learning tasks for grades 5 to 8. The workshop will close with a discussion of general aspects of material-based learning.
5
Johnson, Travis Steele. "Integrative approaches to single cell RNA sequencing analysis." The Ohio State University, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=osu1586960661272666.
Full text
6
Mogofe, Romulus Asaph. "Integrating language literacy skills in teaching physical sciences in Riba Cross District, South Africa." Thesis, University of Limpopo, 2016. http://hdl.handle.net/10386/1590.
Full textAbstract:
Thesis (M. A. (Education)) -- University of Limpopo, 2016Poor performance, by English Language Learners (ELLs), in Science examinations remains a thorny issue in countries where English is not the home language. Research around the world and the Department of Basic Education in South Africa have long recommended the integration of Language Literacy skills in the teaching of Physical Sciences in order to solve this issue. Despite that, learners’ poor performance in Physical Sciences examinations has been found to be positively related to low language literacy skills. The questions are: Do Physical Sciences teachers integrate language literacy skills in teaching the subject?; If yes, to what extent is the integration of language literacy skills practiced in Physical Sciences classroom? In an attempt to answer the above questions, a quantitative survey was carried out in Riba Cross District of Sekhukhune Region of Limpopo Province in South Africa. 211 learners and five teachers from selected nine schools took part in the study and questionnaires were used to collect data. Data were analysed using descriptive and inferential statistics and the Statistical Package for the Social Sciences (SPSS) version 22 was used. The results indicate that Language Literacy skills are integrated into the teaching of Physical Sciences in Riba Cross District, despite concerns raised by the teachers. The areas of concern include letting learners to argue using evidences and writing reports. Furthermore, schools with large classes have challenges in integrating Language Literacy Skills in the teaching of Physical Sciences. Therefore, further studies are recommended which should integrate both qualitative and quantitative approaches in school contexts.
7
Gardner, Trevor. "Wireless Power Transfer Roadway Integration." DigitalCommons@USU, 2017. https://digitalcommons.usu.edu/etd/6866.
Full textAbstract:
Electric vehicles represent a major accomplishment in the energy and transportation industry. Unfortunately, they are restricted to a small travel range because of limited battery life. Successful integration of wireless power transfer (WPT) systems into the infrastructure would remove the range restrictions of EVs. To successfully integrate this technology, several requirements must be met. First, the embedment process cannot interfere with the electrical performance of the inductive power transfer (IPT) system. Second, the presence of the IPT system in the pavement structure cannot negatively affect the roadway’s lifespan.
Several systems were directly embedded in roadway materials. The electrical properties of the systems were monitored during the embedment process. Then modifications were made to the IPT systems to optimize the embedment process. These modifications were then applied to a full scale IPT system which is being used to dynamically charge EVs.
To test the structural performance of the systems, tensile stresses were applied to the pads to simulate traffic loading conditions. These tensile stresses were applied under cyclic loading conditions to simulate fatigue conditions found in roadways. The number of cycles, and stress at failure was recorded an analyzed. The electrical properties of the IPT pads was also measured and analyzed during the fatigue loading conditions.
8
Shell, Jethro. "Fuzzy transfer learning." Thesis, De Montfort University, 2013. http://hdl.handle.net/2086/8842.
Full textAbstract:
The use of machine learning to predict output from data, using a model, is a well studied area. There are, however, a number of real-world applications that require a model to be produced but have little or no data available of the specific environment. These situations are prominent in Intelligent Environments (IEs). The sparsity of the data can be a result of the physical nature of the implementation, such as sensors placed into disaster recovery scenarios, or where the focus of the data acquisition is on very defined user groups, in the case of disabled individuals. Standard machine learning approaches focus on a need for training data to come from the same domain. The restrictions of the physical nature of these environments can severely reduce data acquisition making it extremely costly, or in certain situations, impossible. This impedes the ability of these approaches to model the environments. It is this problem, in the area of IEs, that this thesis is focussed. To address complex and uncertain environments, humans have learnt to use previously acquired information to reason and understand their surroundings. Knowledge from different but related domains can be used to aid the ability to learn. For example, the ability to ride a road bicycle can help when acquiring the more sophisticated skills of mountain biking. This humanistic approach to learning can be used to tackle real-world problems where a-priori labelled training data is either difficult or not possible to gain. The transferral of knowledge from a related, but differing context can allow for the reuse and repurpose of known information. In this thesis, a novel composition of methods are brought together that are broadly based on a humanist approach to learning. Two concepts, Transfer Learning (TL) and Fuzzy Logic (FL) are combined in a framework, Fuzzy Transfer Learning (FuzzyTL), to address the problem of learning tasks that have no prior direct contextual knowledge. Through the use of a FL based learning method, uncertainty that is evident in dynamic environments is represented. By combining labelled data from a contextually related source task, and little or no unlabelled data from a target task, the framework is shown to be able to accomplish predictive tasks using models learned from contextually different data. The framework incorporates an additional novel five stage online adaptation process. By adapting the underlying fuzzy structure through the use of previous labelled knowledge and new unlabelled information, an increase in predictive performance is shown. The framework outlined is applied to two differing real-world IEs to demonstrate its ability to predict in uncertain and dynamic environments. Through a series of experiments, it is shown that the framework is capable of predicting output using differing contextual data.
9
Alexander, John W. "Transfer in reinforcement learning." Thesis, University of Aberdeen, 2015. http://digitool.abdn.ac.uk:80/webclient/DeliveryManager?pid=227908.
Full textAbstract:
The problem of developing skill repertoires autonomously in robotics and artificial intelligence is becoming ever more pressing. Currently, the issues of how to apply prior knowledge to new situations and which knowledge to apply have not been sufficiently studied. We present a transfer setting where a reinforcement learning agent faces multiple problem solving tasks drawn from an unknown generative process, where each task has similar dynamics. The task dynamics are changed by varying in the transition function between states. The tasks are presented sequentially with the latest task presented considered as the target for transfer. We describe two approaches to solving this problem. Firstly we present an algorithm for transfer of the function encoding the stateaction value, defined as value function transfer. This algorithm uses the value function of a source policy to initialise the policy of a target task. We varied the type of basis the algorithm used to approximate the value function. Empirical results in several well known domains showed that the learners benefited from the transfer in the majority of cases. Results also showed that the Radial basis performed better in general than the Fourier. However contrary to expectation the Fourier basis benefited most from the transfer. Secondly, we present an algorithm for learning an informative prior which encodes beliefs about the underlying dynamics shared across all tasks. We call this agent the Informative Prior agent (IP). The prior is learnt though experience and captures the commonalities in the transition dynamics of the domain and allows for a quantification of the agent's uncertainty about these. By using a sparse distribution of the uncertainty in the dynamics as a prior, the IP agent can successfully learn a model of 1) the set of feasible transitions rather than the set of possible transitions, and 2) the likelihood of each of the feasible transitions. Analysis focusing on the accuracy of the learned model showed that IP had a very good accuracy bound, which is expressible in terms of only the permissible error and the diffusion, a factor that describes the concentration of the prior mass around the truth, and which decreases as the number of tasks experienced grows. The empirical evaluation of IP showed that an agent which uses the informative prior outperforms several existing Bayesian reinforcement learning algorithms on tasks with shared structure in a domain where multiple related tasks were presented only once to the learners. IP is a step towards the autonomous acquisition of behaviours in artificial intelligence. IP also provides a contribution towards the analysis of exploration and exploitation in the transfer paradigm.
10
Badley, Kenneth Rea. "Integration" and "the integration of faith and learning." Thesis, University of British Columbia, 1986. http://hdl.handle.net/2429/26769.
Full textAbstract:
This study attempts to determine what use the term "integration" has in educational discourse, specifically as it appears in the popular phrase in Christian higher education, "the integration of faith and learning." Chapter I records that many educators see widespread disintegration in contemporary education. This perceived disintegration has led to many calls and proposals for educational integration. While educators perceive this increased need for integration, what "integration" means is less and less clear.
By surveying actual usage in educational writing, this thesis distinguishes four general senses of "integration": fusion, incorporation, correlation, and dialogical (in Appendix A and Chapter III). It then explores further typical elements of meaning in educational uses of "integration" (Chapter IV). Chapters III and IV reveal and discuss a number of points of contention between educators as to the "meaning of integration."
Chapter V identifies five main sources of the confusion that often accompanies uses of "integration." It is a positive term and frequently is employed primarily for its value as a slogan. Different educators give "integration" at least three different psychological meanings. The same word is used to denote both processes and end states. It is a polymorphous term whose meaning is not clear until what is being integrated is specified. It is a terra that invites conception-building, though conceptions are rarely announced as such; usually educators' visions of what ought to be come cloaked as definitions of terms.
"The integration of faith and learning" suffers from every weakness that "integration" itself encounters. Its popularity in certain sectors of church education is understandable when considered in its historical context: some branches of the church that once largely abandoned higher education are now trying to express a new interest in it. "Integration" is a choice word to serve as a slogan that expresses a certain conception of Christian education. Beyond its function as a slogan, and despite the other problems that frequently accompany its use, "integration" does have use in education, partly because integration is an important concept in education.Education, Faculty of
Graduate
11
Kiehl, Janet K. "Learning to Change: Organizational Learning and Knowledge Transfer." online version, 2004. http://rave.ohiolink.edu/etdc/view?acc%5Fnum=case1080608710.
Full text
12
Elmasry, Sarah Khalil. "Integration Patterns of Learning Technologies." Diss., Virginia Tech, 2007. http://hdl.handle.net/10919/29070.
Full textAbstract:
This research proposes sets of design patterns of learning environments as an innovative approach towards an intelligent architectural design process. These patterns are based on teachers’ spatial and pedagogical use of their learning environments.
The study is based in the desired condition that learning environments are expected to host learning technologies efficiently, to adapt to the fact that its life span is much longer than that of any technology within it, and to accommodate a variation of teaching modes and learning styles. In an effort to address these issues; calls for designing flexible learning spaces have emerged, as well as recommendations for alternative layouts. Yet, more challenging questions emerge; how efficiently do these technologies integrate with other systems in the classroom space? What should architects and facility planners consider for a successful systems’ integration which incorporates learning technologies in the design of the classroom space? And how can these spaces support variations in pedagogical practice. This study attempts to answer these questions by developing a pattern language to support the early design phases of a technology-rich learning environment.
The study is qualitative in nature, and based on interviews with a sample of teachers at academic year Governor’s science and technology schools in Virginia. The researcher attempts to capture problems and challenges related to occupants’ performance within the physical boundaries of the classroom when learning technologies are in use. The variation of teaching-learning modes is taken into consideration.
In this process, the researcher focuses on integration patterns of learning technologies with the envelope and the interior systems. The findings are then translated into the design language in the form of a pattern language at the building systems scale.Ph. D.
13
Johnson, C. Dustin. "Set-Switching and Learning Transfer." Digital Archive @ GSU, 2008. http://digitalarchive.gsu.edu/psych_hontheses/7.
Full textAbstract:
In this experiment I investigated the relationship between set-switching and transfer learning, both of which presumably invoke executive functioning (EF), which may in turn be correlated with intelligence. Set-switching was measured by a computerized version of the Wisconsin Card Sort Task. Another computer task was written to measure learning-transfer ability. The data indicate little correlation between the ability to transfer learning and the capacity for set-switching. That is, these abilities may draw from independent cognitive mechanisms. The major difference may be requirement to utilize previous learning in a new way in the learning-transfer task.
14
Skolidis, Grigorios. "Transfer learning with Gaussian processes." Thesis, University of Edinburgh, 2012. http://hdl.handle.net/1842/6271.
Full textAbstract:
Transfer Learning is an emerging framework for learning from data that aims at intelligently transferring information between tasks. This is achieved by developing algorithms that can perform multiple tasks simultaneously, as well as translating previously acquired knowledge to novel learning problems. In this thesis, we investigate the application of Gaussian Processes to various forms of transfer learning with a focus on classification problems. This process initiates with a thorough introduction to the framework of Transfer learning, providing a clear taxonomy of the areas of research. Following that, we continue by reviewing the recent advances on Multi-task learning for regression with Gaussian processes, and compare the performance of some of these methods on a real data set. This review gives insights about the strengths and weaknesses of each method, which acts as a point of reference to apply these methods to other forms of transfer learning. The main contributions of this thesis are reported in the three following chapters. The third chapter investigates the application of Multi-task Gaussian processes to classification problems. We extend a previously proposed model to the classification scenario, providing three inference methods due to the non-Gaussian likelihood the classification paradigm imposes. The forth chapter extends the multi-task scenario to the semi-supervised case. Using labeled and unlabeled data, we construct a novel covariance function that is able to capture the geometry of the distribution of each task. This setup allows unlabeled data to be utilised to infer the level of correlation between the tasks. Moreover, we also discuss the potential use of this model to situations where no labeled data are available for certain tasks. The fifth chapter investigates a novel form of transfer learning called meta-generalising. The question at hand is if, after training on a sufficient number of tasks, it is possible to make predictions on a novel task. In this situation, the predictor is embedded in an environment of multiple tasks but has no information about the origins of the test task. This elevates the concept of generalising from the level of data to the level of tasks. We employ a model based on a hierarchy of Gaussian processes, in a mixtures of expert sense, to make predictions based on the relation between the distributions of the novel and the training tasks. Each chapter is accompanied with a thorough experimental part giving insights about the potentials and the limits of the proposed methods.
15
Chen, Xiaoyi. "Transfer Learning with Kernel Methods." Thesis, Troyes, 2018. http://www.theses.fr/2018TROY0005.
Full textAbstract:
Le transfert d‘apprentissage regroupe les méthodes permettant de transférer l’apprentissage réalisé sur des données (appelées Source) à des données nouvelles, différentes, mais liées aux données Source. Ces travaux sont une contribution au transfert d’apprentissage homogène (les domaines de représentation des Source et Cible sont identiques) et transductif (la tâche à effectuer sur les données Cible est identique à celle sur les données Source), lorsque nous ne disposons pas d’étiquettes des données Cible. Dans ces travaux, nous relâchons la contrainte d’égalité des lois des étiquettes conditionnellement aux observations, souvent considérée dans la littérature. Notre approche permet de traiter des cas de plus en plus généraux. Elle repose sur la recherche de transformations permettant de rendre similaires les données Source et Cible. Dans un premier temps, nous recherchons cette transformation par Maximum de Vraisemblance. Ensuite, nous adaptons les Machines à Vecteur de Support en intégrant une contrainte additionnelle sur la similitude des données Source et Cible. Cette similitude est mesurée par la Maximum Mean Discrepancy. Enfin, nous proposons l’utilisation de l’Analyse en Composantes Principales à noyau pour rechercher un sous espace, obtenu à partir d’une transformation non linéaire des données Source et Cible, dans lequel les lois des observations sont les plus semblables possibles. Les résultats expérimentaux montrent l’efficacité de nos approchesTransfer Learning aims to take advantage of source data to help the learning task of related but different target data. This thesis contributes to homogeneous transductive transfer learning where no labeled target data is available. In this thesis, we relax the constraint on conditional probability of labels required by covariate shift to be more and more general, based on which the alignment of marginal probabilities of source and target observations renders source and target similar. Thus, firstly, a maximum likelihood based approach is proposed. Secondly, SVM is adapted to transfer learning with an extra MMD-like constraint where Maximum Mean Discrepancy (MMD) measures this similarity. Thirdly, KPCA is used to align data in a RKHS on minimizing MMD. We further develop the KPCA based approach so that a linear transformation in the input space is enough for a good and robust alignment in the RKHS. Experimentally, our proposed approaches are very promising
16
Al, Chalati Abdul Aziz, and Syed Asad Naveed. "Transfer Learning for Machine Diagnostics." Thesis, Högskolan i Halmstad, Akademin för informationsteknologi, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-43185.
Full textAbstract:
Fault detection and diagnostics are crucial tasks in condition-based maintenance. Industries nowadays are in need of fault identification in their machines as early as possible to save money and take precautionary measures in case of fault occurrence. Also, it is beneficial for the smooth interference in the manufacturing process in which it avoids sudden malfunctioning. Having sufficient training data for industrial machines is also a major challenge which is a prerequisite for deep neural networks to train an accurate prediction model. Transfer learning in such cases is beneficial as it can be helpful in adapting different operating conditions and characteristics which is the casein real-life applications. Our work is focused on a pneumatic system which utilizes compressed air to perform operations and is used in different types of machines in the industrial field. Our novel contribution is to build upon a Domain Adversarial Neural Network (DANN) with a unique approach by incorporating ensembling techniques for diagnostics of air leakage problem in the pneumatic system under transfer learning settings. Our approach of using ensemble methods for feature extraction shows up to 5 % improvement in the performance. We have also performed a comparative analysis of our work with conventional machine and deep learning methods which depicts the importance of transfer learning and we have also demonstrated the generalization ability of our model. Lastly, we also mentioned a problem specific contribution by suggesting a feature engineering approach, such that it could be implemented on almost every pneumatic system and could potentially impact the prediction result positively. We demonstrate that our designed model with domain adaptation ability will be quite useful and beneficial for the industry by saving their time and money and providing promising results for this air leakage problem in the pneumatic system.
17
Lu, Ying. "Transfer Learning for Image Classification." Thesis, Lyon, 2017. http://www.theses.fr/2017LYSEC045/document.
Full textAbstract:
Lors de l’apprentissage d’un modèle de classification pour un nouveau domaine cible avec seulement une petite quantité d’échantillons de formation, l’application des algorithmes d’apprentissage automatiques conduit généralement à des classifieurs surdimensionnés avec de mauvaises compétences de généralisation. D’autre part, recueillir un nombre suffisant d’échantillons de formation étiquetés manuellement peut s’avérer très coûteux. Les méthodes de transfert d’apprentissage visent à résoudre ce type de problèmes en transférant des connaissances provenant d’un domaine source associé qui contient beaucoup plus de données pour faciliter la classification dans le domaine cible. Selon les différentes hypothèses sur le domaine cible et le domaine source, l’apprentissage par transfert peut être classé en trois catégories: apprentissage par transfert inductif, apprentissage par transfert transducteur (adaptation du domaine) et apprentissage par transfert non surveillé. Nous nous concentrons sur le premier qui suppose que la tâche cible et la tâche source sont différentes mais liées. Plus précisément, nous supposons que la tâche cible et la tâche source sont des tâches de classification, tandis que les catégories cible et les catégories source sont différentes mais liées. Nous proposons deux méthodes différentes pour aborder ce problème. Dans le premier travail, nous proposons une nouvelle méthode d’apprentissage par transfert discriminatif, à savoir DTL(Discriminative Transfer Learning), combinant une série d’hypothèses faites à la fois par le modèle appris avec les échantillons de cible et les modèles supplémentaires appris avec des échantillons des catégories sources. Plus précisément, nous utilisons le résidu de reconstruction creuse comme discriminant de base et améliore son pouvoir discriminatif en comparant deux résidus d’un dictionnaire positif et d’un dictionnaire négatif. Sur cette base, nous utilisons des similitudes et des dissemblances en choisissant des catégories sources positivement corrélées et négativement corrélées pour former des dictionnaires supplémentaires. Une nouvelle fonction de coût basée sur la statistique de Wilcoxon-Mann-Whitney est proposée pour choisir les dictionnaires supplémentaires avec des données non équilibrées. En outre, deux processus de Boosting parallèles sont appliqués à la fois aux distributions de données positives et négatives pour améliorer encore les performances du classificateur. Sur deux bases de données de classification d’images différentes, la DTL proposée surpasse de manière constante les autres méthodes de l’état de l’art du transfert de connaissances, tout en maintenant un temps d’exécution très efficace. Dans le deuxième travail, nous combinons le pouvoir du transport optimal (OT) et des réseaux de neurones profond (DNN) pour résoudre le problème ITL. Plus précisément, nous proposons une nouvelle méthode pour affiner conjointement un réseau de neurones avec des données source et des données cibles. En ajoutant une fonction de perte du transfert optimal (OT loss) entre les prédictions du classificateur source et cible comme une contrainte sur le classificateur source, le réseau JTLN (Joint Transfer Learning Network) proposé peut effectivement apprendre des connaissances utiles pour la classification cible à partir des données source. En outre, en utilisant différents métriques comme matrice de coût pour la fonction de perte du transfert optimal, JTLN peut intégrer différentes connaissances antérieures sur la relation entre les catégories cibles et les catégories sources. Nous avons effectué des expérimentations avec JTLN basées sur Alexnet sur les jeux de données de classification d’image et les résultats vérifient l’efficacité du JTLN proposé. A notre connaissances, ce JTLN proposé est le premier travail à aborder ITL avec des réseaux de neurones profond (DNN) tout en intégrant des connaissances antérieures sur la relation entre les catégories cible et sourceWhen learning a classification model for a new target domain with only a small amount of training samples, brute force application of machine learning algorithms generally leads to over-fitted classifiers with poor generalization skills. On the other hand, collecting a sufficient number of manually labeled training samples may prove very expensive. Transfer Learning methods aim to solve this kind of problems by transferring knowledge from related source domain which has much more data to help classification in the target domain. Depending on different assumptions about target domain and source domain, transfer learning can be further categorized into three categories: Inductive Transfer Learning, Transductive Transfer Learning (Domain Adaptation) and Unsupervised Transfer Learning. We focus on the first one which assumes that the target task and source task are different but related. More specifically, we assume that both target task and source task are classification tasks, while the target categories and source categories are different but related. We propose two different methods to approach this ITL problem. In the first work we propose a new discriminative transfer learning method, namely DTL, combining a series of hypotheses made by both the model learned with target training samples, and the additional models learned with source category samples. Specifically, we use the sparse reconstruction residual as a basic discriminant, and enhance its discriminative power by comparing two residuals from a positive and a negative dictionary. On this basis, we make use of similarities and dissimilarities by choosing both positively correlated and negatively correlated source categories to form additional dictionaries. A new Wilcoxon-Mann-Whitney statistic based cost function is proposed to choose the additional dictionaries with unbalanced training data. Also, two parallel boosting processes are applied to both the positive and negative data distributions to further improve classifier performance. On two different image classification databases, the proposed DTL consistently out performs other state-of-the-art transfer learning methods, while at the same time maintaining very efficient runtime. In the second work we combine the power of Optimal Transport and Deep Neural Networks to tackle the ITL problem. Specifically, we propose a novel method to jointly fine-tune a Deep Neural Network with source data and target data. By adding an Optimal Transport loss (OT loss) between source and target classifier predictions as a constraint on the source classifier, the proposed Joint Transfer Learning Network (JTLN) can effectively learn useful knowledge for target classification from source data. Furthermore, by using different kind of metric as cost matrix for the OT loss, JTLN can incorporate different prior knowledge about the relatedness between target categories and source categories. We carried out experiments with JTLN based on Alexnet on image classification datasets and the results verify the effectiveness of the proposed JTLN in comparison with standard consecutive fine-tuning. To the best of our knowledge, the proposed JTLN is the first work to tackle ITL with Deep Neural Networks while incorporating prior knowledge on relatedness between target and source categories. This Joint Transfer Learning with OT loss is general and can also be applied to other kind of Neural Networks
18
Arnekvist, Isac. "Transfer Learning using low-dimensional Representations in Reinforcement Learning." Licentiate thesis, KTH, Robotik, perception och lärande, RPL, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-279120.
Full textAbstract:
Successful learning of behaviors in Reinforcement Learning (RL) are often learned tabula rasa, requiring many observations and interactions in the environment. Performing this outside of a simulator, in the real world, often becomes infeasible due to the large amount of interactions needed. This has motivated the use of Transfer Learning for Reinforcement Learning, where learning is accelerated by using experiences from previous learning in related tasks. In this thesis, I explore how we can transfer from a simple single-object pushing policy, to a wide array of non-prehensile rearrangement problems. I then explain how we can model task differences using a low-dimensional latent variable representation to make adaption to novel tasks efficient. Lastly, the dependence of accurate function approximation is sometimes problematic, especially in RL, where statistics of target variables are not known a priori. I present observations, along with explanations, that small target variances along with momentum optimization of ReLU-activated neural network parameters leads to dying ReLU.Framgångsrik inlärning av beteenden inom ramen för Reinforcement Learning (RL) sker ofta tabula rasa och kräver stora mängder observationer och interaktioner. Att använda RL-algoritmer utanför simulering, i den riktiga världen, är därför ofta inte praktiskt utförbart. Detta har motiverat studier i Transfer Learning för RL, där inlärningen accelereras av erfarenheter från tidigare inlärning av liknande uppgifter. I denna licentiatuppsats utforskar jag hur vi kan vi kan åstadkomma transfer från en enklare manipulationspolicy, till en större samling omarrangeringsproblem. Jag fortsätter sedan med att beskriva hur vi kan modellera hur olika inlärningsproblem skiljer sig åt med hjälp av en lågdimensionell parametrisering, och på så vis effektivisera inlärningen av nya problem. Beroendet av bra funktionsapproximation är ibland problematiskt, särskilt inom RL där statistik om målvariabler inte är kända i förväg. Jag presenterar därför slutligen observationer, och förklaringar, att små varianser för målvariabler tillsammans med momentum-optimering leder till dying ReLU.
QC 20200819
19
Mare, Angelique. "Motivators of learning and learning transfer in the workplace." Diss., University of Pretoria, 2015. http://hdl.handle.net/2263/52441.
Full textAbstract:
Motivating employees to learn and transfer their learning to their jobs is an important activity to ensure that employees - and the organisation - continuously adapt, evolve and survive in this highly turbulent environment. The literature shows that both intrinsic and extrinsic motivators influence learning and learning transfer, and the extent of influence could be different for different people. This research sets out to explore and identify the intrinsic and extrinsic motivational factors that drive learning and learning transfer.
A qualitative study in the form of focus groups was conducted. Three focus groups were conducted in which a total of 25 middle managers from two different multinational companies participated. Content and frequency analysis were used to identify the key themes from the focus group discussion.
The outcome of the study resulted in the identification of the key intrinsic and extrinsic motivation factors that drive learning and learning transfer. The findings have been used to develop a Motivation-to-learn-and-transfer catalyst framework indicating that individual intrinsic motivators are at the core of driving motivation to learn and transfer learning. It also indicates which training design and work environment factors to focus on in support of intrinsic motivation to learn and transfer learning in the workplace for middle managers. It is hoped that the outcome of this research will contribute to catalysing learning and learning transfer for middle managers to achieve higher organisational effectiveness.Mini Dissertation (MBA)--University of Pretoria, 2015.
pa2016
Gordon Institute of Business Science (GIBS)
MBA
Unrestricted
20
Frenger, Tobias, and Johan Häggmark. "Transfer learning between domains : Evaluating the usefulness of transfer learning between object classification and audio classification." Thesis, Högskolan i Skövde, Institutionen för informationsteknologi, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-18669.
Full textAbstract:
Convolutional neural networks have been successfully applied to both object classification and audio classification. The aim of this thesis is to evaluate the degree of how well transfer learning of convolutional neural networks, trained in the object classification domain on large datasets (such as CIFAR-10, and ImageNet), can be applied to the audio classification domain when only a small dataset is available. In this work, four different convolutional neural networks are tested with three configurations of transfer learning against a configuration without transfer learning. This allows for testing how transfer learning and the architectural complexity of the networks affects the performance. Two of the models developed by Google (Inception-V3, Inception-ResNet-V2), are used. These models are implemented using the Keras API where they are pre-trained on the ImageNet dataset. This paper also introduces two new architectures which are developed by the authors of this thesis. These are Mini-Inception, and Mini-Inception-ResNet, and are inspired by Inception-V3 and Inception-ResNet-V2, but with a significantly lower complexity. The audio classification dataset consists of audio from RC-boats which are transformed into mel-spectrogram images. For transfer learning to be possible, Mini-Inception, and Mini-Inception-ResNet are pre-trained on the dataset CIFAR-10. The results show that transfer learning is not able to increase the performance. However, transfer learning does in some cases enable models to obtain higher performance in the earlier stages of training.
21
Bizonova, Zuzana. "Model driven e-learning platform integration." Evry, Télécom & Management SudParis, 2008. http://www.theses.fr/2008TELE0011.
Full textAbstract:
Le travail présenté ici s’intéresse à la problématique de l’interopérabilité entre systèmes de téléenseignement (e-learning) ; en particulier en ce qui concerne la question de la réutilisation des didacticiels (coursewares), sujets d’investissements considérables de la part des auteurs. En effet, le succès du paradigme du téléenseignement a été tel qu’il a donné lieu au développement de nombreuses plateformes toujours plus complexes et puissantes, mais reposant sur des architectures diverses, aux interfaces variées et incompatibles. Le résultat est une isolation croissante des applications (les systèmes de téléenseignement) et des données (les didacticiels), au détriment de la pérennité des investissements effectués dans ces derniers. L’approche retenue a utilisé le Model Driven Architecture (MDA) comme base conceptuelle. La stratégie, résumée à grands traits, a été la suivante : - Un travail approfondi sur les architectures des systèmes cibles a permis de dégager les principes architecturaux de ces diverses plateformes ; - L’étape suivante impliquait de disposer d’une modélisation générique (Platform Independent Model ou PIM du MDA) des systèmes cibles, de façon à pouvoir instancier un tel modèle en modèles plus concrets (Platform Specific Model ou PSM, puis implémentation). Une réflexion théorique a permis de conjecturer, puis de mettre au point une méthode originale intégrée au MDA, introduisant une étape de rétro-conception. L’application de cette méthode sur les systèmes cibles a résulté en l’obtention d’un modèle générique PIM généralisant l’ensemble des systèmes cibles en un seul modèle indépendant des plateformes. - Le modèle PIM généralisé a finalement permis de spécifier et d’implémenter un démonstrateur logiciel capable de migrer automatiquement des données (didacticiels) entre les plateformes ciblesIn the recent years, e-learning gained popularity among educational institutions as well as enterprises. As the result of that many commercial or open-source Learning Management Systems (LMS) were developed to manage online courses. However, while the usage of these systems gained recognition and acceptance amongst institutions, a new category of problems arose that needs to be solved: because of multiplicity of platforms and approaches used for various systems implementation, it became increasingly difficult to exchange pieces of information among those systems. Applications and their data become isolated - a clear economical concern for the future of these technologies. The present study describes a method, based on Model Driven Architecture (MDA), for integrating approaches of candidate LMS systems into a generalized architectural framework. The framework makes use of standards for description of data and metadata like learning materials (IEEE LOM, IEEE PAPI), student information (IMS LIP) or learning design (IMS LD). This platform-independent framework can be used for automatic migration of data between various e-learning platforms
Počas posledných desiatich rokov si e-learning získal popularitu medzi vzdelávacími inštitúciami po celom svete. Výsledkom tohto trendu bola tvorba mnohých Learning Management Systémov na správu e-learningových kurzov. Mnohé z týchto systémov získavajú stále väčší počet používateľov avšak začínajú sa objavovať nové problémy spojené s ich používaním. Množstvo rôznorodých systémov a platforiem spôsobuje problémy pri zdieľaní dát medzi nimi. Tieto aplikácie a ich dáta ostávajú navzájom medzi sebou v izolácii, čo však môže spôsobiť vážne ekonomické problémy a ohroziť budúcnosť týchto technológií. Pre lepšie pochopenie, ide tu o zdieľanie takých dát ako sú vzdelávacie materiály či záznamy a výsledky jednotlivých študentov. Vytvorenie kvalitného materiálu je časovo aj myšlienkovo náročný process. Ak nie je možné zdieľať tieto dáta medzi systémami, znamená to, že je problematické ich znovuvyužitie v inej platforme. V tejto situácii je potrebné opakovane vytvárať rovnaké druhy informácií pre rozličné systémy. Táto štúdia opisuje metódu založenú na Modelovo orientovanej architektúre (MDA), ktorá integruje prístupy rozličných pozorovaných LMS systémov do zovšeobecného architektonického rámca, ktorý využíva štandardy pre popis dát a metadát ako napríklad IEEE LOM, IMS QTI či IEEE PAPI alebo IMS LD. Tento platformovo nezávislý rámec nám umožní automaticke zdieľanie rozličných druhov dát medzi e-learningovými platformami
22
Redko, Ievgen. "Nonnegative matrix factorization for transfer learning." Thesis, Sorbonne Paris Cité, 2015. http://www.theses.fr/2015USPCD059.
Full textAbstract:
L’apprentissage par transfert consiste `a utiliser un jeu de taches pour influencerl’apprentissage et améliorer les performances sur une autre tache.Cependant, ce paradigme d’apprentissage peut en réalité gêner les performancessi les taches (sources et cibles) sont trop dissemblables. Un défipour l’apprentissage par transfert est donc de développer des approchesqui détectent et évitent le transfert négatif des connaissances utilisant tr`espeu d’informations sur la tache cible. Un cas particulier de ce type d’apprentissageest l’adaptation de domaine. C’est une situation o`u les tachessources et cibles sont identiques mais dans des domaines différents. Danscette thèse, nous proposons des approches adaptatives basées sur la factorisationmatricielle non-figurative permettant ainsi de trouver une représentationadéquate des données pour ce type d’apprentissage. En effet, unereprésentation utile rend généralement la structure latente dans les donnéesexplicite, et réduit souvent la dimensionnalité´e des données afin que d’autresméthodes de calcul puissent être appliquées. Nos contributions dans cettethèse s’articulent autour de deux dimensions complémentaires : théoriqueet pratique.Tout d’abord, nous avons propose deux méthodes différentes pour résoudrele problème de l’apprentissage par transfert non supervise´e bas´e sur destechniques de factorisation matricielle non-négative. La première méthodeutilise une procédure d’optimisation itérative qui vise `a aligner les matricesde noyaux calculées sur les bases des données provenant de deux taches.La seconde représente une approche linéaire qui tente de découvrir unplongement pour les deux taches minimisant la distance entre les distributionsde probabilité correspondantes, tout en préservant la propriété depositivité.Nous avons également propos´e un cadre théorique bas´e sur les plongementsHilbert-Schmidt. Cela nous permet d’améliorer les résultats théoriquesde l’adaptation au domaine, en introduisant une mesure de distancenaturelle et intuitive avec de fortes garanties de calcul pour son estimation.Les résultats propos´es combinent l’etancheite des bornes de la théoried’apprentissage de Rademacher tout en assurant l’estimation efficace deses facteurs cl´es.Les contributions théoriques et algorithmiques proposées ont et évaluéessur un ensemble de données de référence dans le domaine avec des résultatsprometteursThe ability of a human being to extrapolate previously gained knowledge to other domains inspired a new family of methods in machine learning called transfer learning. Transfer learning is often based on the assumption that objects in both target and source domains share some common feature and/or data space. If this assumption is false, most of transfer learning algorithms are likely to fail. In this thesis we propose to investigate the problem of transfer learning from both theoretical and applicational points of view.First, we present two different methods to solve the problem of unsuper-vised transfer learning based on Non-negative matrix factorization tech-niques. First one proceeds using an iterative optimization procedure that aims at aligning the kernel matrices calculated based on the data from two tasks. Second one represents a linear approach that aims at discovering an embedding for two tasks that decreases the distance between the cor-responding probability distributions while preserving the non-negativity property.We also introduce a theoretical framework based on the Hilbert-Schmidt embeddings that allows us to improve the current state-of-the-art theo-retical results on transfer learning by introducing a natural and intuitive distance measure with strong computational guarantees for its estimation. The proposed results combine the tightness of data-dependent bounds de-rived from Rademacher learning theory while ensuring the efficient esti-mation of its key factors.Both theoretical contributions and the proposed methods were evaluated on a benchmark computer vision data set with promising results. Finally, we believe that the research direction chosen in this thesis may have fruit-ful implications in the nearest future
23
Mallia, Gorg. "Transfer of learning from literature lessons." Thesis, University of Sheffield, 2002. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.274972.
Full text
24
Quattoni, Ariadna J. "Transfer learning algorithms for image classification." Thesis, Massachusetts Institute of Technology, 2009. http://hdl.handle.net/1721.1/53294.
Full textAbstract:
Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2009.Cataloged from PDF version of thesis.
Includes bibliographical references (p. 124-128).
An ideal image classifier should be able to exploit complex high dimensional feature representations even when only a few labeled examples are available for training. To achieve this goal we develop transfer learning algorithms that: 1) Leverage unlabeled data annotated with meta-data and 2) Exploit labeled data from related categories. In the first part of this thesis we show how to use the structure learning framework (Ando and Zhang, 2005) to learn efficient image representations from unlabeled images annotated with meta-data. In the second part we present a joint sparsity transfer algorithm for image classification. Our algorithm is based on the observation that related categories might be learnable using only a small subset of shared relevant features. To find these features we propose to train classifiers jointly with a shared regularization penalty that minimizes the total number of features involved in the approximation. To solve the joint sparse approximation problem we develop an optimization algorithm whose time and memory complexity is O(n log n) with n being the number of parameters of the joint model. We conduct experiments on news-topic and keyword prediction image classification tasks. We test our method in two settings: a transfer learning and multitask learning setting and show that in both cases leveraging knowledge from related categories can improve performance when training data per category is scarce. Furthermore, our results demonstrate that our model can successfully recover jointly sparse solutions.
by Ariadna Quattoni.
Ph.D.
25
Aytar, Yusuf. "Transfer learning for object category detection." Thesis, University of Oxford, 2014. http://ora.ox.ac.uk/objects/uuid:c9e18ff9-df43-4f67-b8ac-28c3fdfa584b.
Full textAbstract:
Object category detection, the task of determining if one or more instances of a category are present in an image with their corresponding locations, is one of the fundamental problems of computer vision. The task is very challenging because of the large variations in imaged object appearance, particularly due to the changes in viewpoint, illumination and intra-class variance. Although successful solutions exist for learning object category detectors, they require massive amounts of training data. Transfer learning builds upon previously acquired knowledge and thus reduces training requirements. The objective of this work is to develop and apply novel transfer learning techniques specific to the object category detection problem. This thesis proposes methods which not only address the challenges of performing transfer learning for object category detection such as finding relevant sources for transfer, handling aspect ratio mismatches and considering the geometric relations between the features; but also enable large scale object category detection by quickly learning from considerably fewer training samples and immediate evaluation of models on web scale data with the help of part-based indexing. Several novel transfer models are introduced such as: (a) rigid transfer for transferring knowledge between similar classes, (b) deformable transfer which tolerates small structural changes by deforming the source detector while performing the transfer, and (c) part level transfer particularly for the cases where full template transfer is not possible due to aspect ratio mismatches or not having adequately similar sources. Building upon the idea of using part-level transfer, instead of performing an exhaustive sliding window search, part-based indexing is proposed for efficient evaluation of templates enabling us to obtain immediate detection results in large scale image collections. Furthermore, easier and more robust optimization methods are developed with the help of feature maps defined between proposed transfer learning formulations and the “classical” SVM formulation.
26
Farajidavar, Nazli. "Transductive transfer learning for computer vision." Thesis, University of Surrey, 2015. http://epubs.surrey.ac.uk/807998/.
Full textAbstract:
Artificial intelligent and machine learning technologies have already achieved significant success in classification, regression and clustering. However, many machine learning methods work well only under a common assumption that training and test data are drawn from the same feature space and the same distribution. A real world applications is in sports footage, where an intelligent system has been designed and trained to detect score-changing events in a Tennis single match and we are interested to transfer this learning to either Tennis doubles game or even a more challenging domain such as Badminton. In such distribution changes, most statistical models need to be rebuilt, using newly collected training data. In many real world applications, it is expensive or even impossible to collect the required training data and rebuild the models. One of the ultimate goals of the open ended learning systems is to take advantage of previous experience/ knowledge in dealing with similar future problems. Two levels of learning can be identified in such scenarios. One draws on the data by capturing the pattern and regularities which enables reliable predictions on new samples. The other starts from an acquired source of knowledge and focuses on how to generalise it to a new target concept; this is also known as transfer learning which is going to be the main focus of this thesis. This work is devoted to a second level of learning by focusing on how to transfer information from previous learnings, exploiting it on a new learning problem with not supervisory information available for new target data. We propose several solutions to such tasks by leveraging over prior models or features. In the first part of the thesis we show how to estimate reliable transformations from the source domain to the target domain with the aim of reducing the dissimilarities between the source class-conditional distribution and a new unlabelled target distribution. We then later present a fully automated transfer learning framework which approaches the problem by combining four types of adaptation: a projection to lower dimensional space that is shared between the two domains, a set of local transformations to further increase the domain similarity, a classifier parameter adaptation method which modifies the learner for the new domain and a set of class-conditional transformations aiming to increase the similarity between the posterior probability of samples in the source and target sets. We conduct experiments on a wide range of image and video classification tasks. We test our proposed methods and show that, in all cases, leveraging knowledge from a related domain can improve performance when there are no labels available for direct training on the new target data.
27
Jamil, Ahsan Adnan, and Daniel Landberg. "Detecting COVID-19 Using Transfer Learning." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-280352.
Full textAbstract:
COVID-19 is currently an ongoing pandemic and the large demand for testing of the disease has led to insufficient resources in hospitals. In order to increase the efficiency of COVID- 19 detection, computer vision based systems can be used. However, a large set of training data is required for creating an accurate and reliable model, which is currently not feasible to be acquired considering the novelty of the disease. Other models are currently being used within the healthcare sector for classifying various diseases, one such model is for identifying pneumonia cases by using radiographs and it has achieved high enough accuracy to be used on patients [18]. With the background of having limited data for COVID-19 identification, this thesis evaluates the benefit of using transfer learning in order to augment the performance of the COVID-19 detection model. By using pneumonia dataset as a base for feature extraction the goal is to generate a COVID-19 classifier through transfer learning. Using transfer learning, an accuracy of 97% was achieved, compared to the initial accuracy of 32% when transfer learning was not used.COVID-19 är för närvarande en pågående pandemi och det är en stor efterfrågan på tester, Vilket har lett till att resurserna på sjukhusen inte räcker till. I syfte att öka effektiviteten för COVID-19 tester kan datorsynbaserade system användas. En datorsynsbaserad klassificerare kräver en stor uppsättning träningsdata för att kunna skapa en noggrann och pålitlig modell, vilket för närvarande inte är tillgängligt eftersom sjukdomen endast har existerat i några månader. Diverse modeller används inom sjukvårdssektorn för klassificering av olika sjukdomar. Klassificering av lunginflammationsfall med hjälp av röntgenbilder är ett av de områden där modeller används. Modellerna har uppnått tillräckligt hög noggrannhet för att kunna användas på patienter [18]. Eftersom datamängden är begränsad för identifiering av COVID-19 utvärderar detta arbete nyttan med att använda överföringsinlärning i syfte att förbättra prestandan i COVID-19-detekteringsmodeller. Genom att använda Lunginflammations bilder som en bas för extraktion av attribut, är målet att generera en COVID-19 klassificerare genom överföringsinlärning. Med användning av denna metod uppnåddes en noggrannhet på 97 % jämfört med den ursprungliga noggrannheten på 32 % när överföringsinlärning inte användes.
28
Mendoza-Schrock, Olga L. "Diffusion Maps and Transfer Subspace Learning." Wright State University / OhioLINK, 2017. http://rave.ohiolink.edu/etdc/view?acc_num=wright1503964976467066.
Full text
29
Kumar, Sharad. "Localizing Little Landmarks with Transfer Learning." PDXScholar, 2019. https://pdxscholar.library.pdx.edu/open_access_etds/4827.
Full textAbstract:
Locating a small object in an image -- like a mouse on a computer desk or the door handle of a car -- is an important computer vision problem to solve because in many real life situations a small object may be the first thing that gets operated upon in the image scene. While a significant amount of artificial intelligence and machine learning research has focused on localizing prominent objects in an image, the area of small object detection has remained less explored. In my research I explore the possibility of using context information to localize small objects in an image. Using a Convolutional Neural Network (CNN), I create a regression model to detect a small object in an image where model training is supervised by coordinates of the small object in the image. Since small objects do not have strong visual characteristics in an image, it's difficult for a neural network to discern their pattern because their feature map exhibits low resolution rendering a much weaker signal for the network to recognize. Use of context for object detection and localization has been studied for a long time. This idea is explored by Singh et al. for small object localization by using a multi-step regression process where spatial context is used effectively to localize small objects in several datasets. I extend the idea in this research and demonstrate that the technique of localizing in steps using contextual information when used with transfer learning can significantly reduce model training time.
30
Lieu, Jenny. "Influences of policy learning, transfer, and post transfer learning in the development of China's wind power policies." Thesis, University of Sussex, 2013. http://sro.sussex.ac.uk/id/eprint/46453/.
Full textAbstract:
China's renewable energy (RE) sector is developing rapidly, driven by growing energy needs, increased awareness of climate change, and heightened concerns for environmental degradation caused by the country's industrialisation process over the past decades. The Chinese government has been dedicated to the development of its RE industry and has engaged extensively in drawing lessons from abroad and applying these lessons to its own experiences in the post transfer learning process to develop policies that have contributed to the development of the largest wind power sector in the world. This thesis provides a perspective of how China, a ‘socialist market economy', has applied primarily market mechanisms from liberalised market systems found in Western Europe and the United States to develop its domestic wind power sector. Having similar economic, political and cultural value systems is not necessarily a prerequisite to policy learning; rather policy objective compatibility is a more important criterion when drawing and transferring lessons. The objective of this thesis is to analyse how the policy learning from abroad, policy transfer and the post transfer process has influenced the development of wind power policies in China through the application of a framework to analyse the policies. The framework was specifically developed for this thesis and was largely based on policy learning and policy transfer concepts as well as general learning literature. Using the wind power policies in China as a case study, this thesis identifies elements of policy learning from abroad and examines how transferred policies have been applied in first level policies that are top-level coordinating policies (e.g. mid- to long-term strategies and frameworks) as well as second level policies, with specific objectives focusing on diffusion and adoption (e.g. renewable energy policy instruments). Overall, studying policy learning from abroad, policy transfer and the post transfer process contributes to understanding how learning across political boarders contributes to the domestic policy formation and implementation process.
31
Pettersson, Harald. "Sentiment analysis and transfer learning using recurrent neural networks : an investigation of the power of transfer learning." Thesis, Linköpings universitet, Interaktiva och kognitiva system, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-161348.
Full textAbstract:
In the field of data mining, transfer learning is the method of transferring knowledge from one domain into another. Using reviews from prisjakt.se, a Swedish price comparison site, and hotels.com this work investigate how the similarities between domains affect the results of transfer learning when using recurrent neural networks. We test several different domains with different characteristics, e.g. size and lexical similarity. In this work only relatively similar domains were used, the same target function was sought and all reviews were in Swedish. Regardless, the results are conclusive; transfer learning is often beneficial, but is highly dependent on the features of the domains and how they compare with each other’s.
32
Andersen, Linda, and Philip Andersson. "Deep Learning Approach for Diabetic Retinopathy Grading with Transfer Learning." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-279981.
Full textAbstract:
Diabetic retinopathy (DR) is a complication of diabetes and is a disease that affects the eyes. It is one of the leading causes of blindness in the Western world. As the number of people with diabetes grows globally, so does the number of people affected by diabetic retinopathy. This demand requires that better and more effective resources are developed in order to discover the disease in an early stage which is key to preventing that the disease progresses into more serious stages which ultimately could lead to blindness, and streamline further treatment of the disease. However, traditional manual screenings are not enough to meet this demand. This is where the role of computer-aided diagnosis comes in. The purpose of this report is to investigate how a convolutional neural network together with transfer learning can perform when trained for multiclass grading of diabetic retinopathy. In order to do this, a pre-built and pre-trained convolutional neural network from Keras was used and further trained and fine-tuned in Tensorflow on a 5-class DR grading dataset. Twenty training sessions were performed and accuracy, recall and specificity were evaluated in each session. The results show that testing accuracies achieved were in the range of 35% to 48.5%. The average testing recall achieved for class 0, 1, 2, 3 and 4 was 59.7%, 0.0%, 51.0%, 38.7% and 0.8%, respectively. Furthermore, the average testing specificity achieved for class 0, 1, 2, 3 and 4 was 77.8%, 100.0%, 62.4%, 80.2% and 99.7%, respectively. The average recall of 0.0% and average specificity of 100.0% for class 1 (mild DR) were obtained because the CNN model never predicted this class.Diabetisk näthinnesjukdom (DR) är en komplikation av diabetes och är en sjukdom som påverkar ögonen. Det är en av de största orsakerna till blindhet i västvärlden. Allt eftersom antalet människor med diabetes ökar, ökar även antalet med diabetisk näthinnesjukdom. Detta ställer högre krav på att bättre och effektivare resurser utvecklas för att kunna upptäcka sjukdomen i ett tidigt stadie, vilket är en förutsättning för att förhindra vidareutveckling av sjukdomen som i slutändan kan resultera i blindhet, och att vidare behandling av sjukdomen effektiviseras. Här spelar datorstödd diagnostik en viktig roll. Syftet med denna studie är att undersöka hur ett faltningsnätverk, tillsammans med överföringsinformation, kan prestera när det tränas för multiklass gradering av diabetisk näthinnesjukdom. För att göra detta användes ett färdigbyggt och färdigtränat faltningsnätverk, byggt i Keras, för att fortsättningsvis tränas och finjusteras i Tensorflow på ett 5-klassigt DR dataset. Totalt tjugo träningssessioner genomfördes och noggrannhet, sensitivitet och specificitet utvärderades i varje sådan session. Resultat visar att de uppnådda noggranheterna låg inom intervallet 35% till 48.5%. Den genomsnittliga testsensitiviteten för klass 0, 1, 2, 3 och 4 var 59.7%, 0.0%, 51.0%, 38.7% respektive 0.8%. Vidare uppnåddes en genomsnittlig testspecificitet för klass 1, 2, 3 och 4 på 77.8%, 100.0%, 62.4%, 80.2% respektive 99.7%. Den genomsnittliga sensitiviteten på 0.0% samt den genomsnittliga specificiteten på 100.0% för klass 1 (mild DR) erhölls eftersom CNN modellen aldrig förutsåg denna klass.
33
Choi, Jin-Woo. "Action Recognition with Knowledge Transfer." Diss., Virginia Tech, 2021. http://hdl.handle.net/10919/101780.
Full textAbstract:
Recent progress on deep neural networks has shown remarkable action recognition performance from videos. The remarkable performance is often achieved by transfer learning: training a model on a large-scale labeled dataset (source) and then fine-tuning the model on the small-scale labeled datasets (targets). However, existing action recognition models do not always generalize well on new tasks or datasets because of the following two reasons. i) Current action recognition datasets have a spurious correlation between action types and background scene types. The models trained on these datasets are biased towards the scene instead of focusing on the actual action. This scene bias leads to poor generalization performance. ii) Directly testing the model trained on the source data on the target data leads to poor performance as the source, and target distributions are different. Fine-tuning the model on the target data can mitigate this issue. However, manual labeling small- scale target videos is labor-intensive. In this dissertation, I propose solutions to these two problems. For the first problem, I propose to learn scene-invariant action representations to mitigate the scene bias in action recognition models. Specifically, I augment the standard cross-entropy loss for action classification with 1) an adversarial loss for the scene types and 2) a human mask confusion loss for videos where the human actors are invisible. These two losses encourage learning representations unsuitable for predicting 1) the correct scene types and 2) the correct action types when there is no evidence. I validate the efficacy of the proposed method by transfer learning experiments. I trans- fer the pre-trained model to three different tasks, including action classification, temporal action localization, and spatio-temporal action detection. The results show consistent improvement over the baselines for every task and dataset. I formulate human action recognition as an unsupervised
domain adaptation (UDA) problem to handle the second problem. In the UDA setting, we have many labeled videos as source data and unlabeled videos as target data. We can use already exist- ing labeled video datasets as source data in this setting. The task is to align the source and target feature distributions so that the learned model can generalize well on the target data. I propose 1) aligning the more important temporal part of each video and 2) encouraging the model to focus on action, not the background scene, to learn domain-invariant action representations. The proposed method is simple and intuitive while achieving state-of-the-art performance without training on a lot of labeled target videos. I relax the unsupervised target data setting to a sparsely labeled target data setting. Then I explore the semi-supervised video action recognition, where we have a lot of labeled videos as source data and sparsely labeled videos as target data. The semi-supervised setting is practical as sometimes we can afford a little bit of cost for labeling target data. I propose multiple video data augmentation methods to inject photometric, geometric, temporal, and scene invariances to the action recognition model in this setting. The resulting method shows favorable performance on the public benchmarks.Doctor of Philosophy
Recent progress on deep learning has shown remarkable action recognition performance. The remarkable performance is often achieved by transferring the knowledge learned from existing large-scale data to the small-scale data specific to applications. However, existing action recog- nition models do not always work well on new tasks and datasets because of the following two problems. i) Current action recognition datasets have a spurious correlation between action types and background scene types. The models trained on these datasets are biased towards the scene instead of focusing on the actual action. This scene bias leads to poor performance on the new datasets and tasks. ii) Directly testing the model trained on the source data on the target data leads to poor performance as the source, and target distributions are different. Fine-tuning the model on the target data can mitigate this issue. However, manual labeling small-scale target videos is labor-intensive. In this dissertation, I propose solutions to these two problems. To tackle the first problem, I propose to learn scene-invariant action representations to mitigate background scene- biased human action recognition models for the first problem. Specifically, the proposed method learns representations that cannot predict the scene types and the correct actions when there is no evidence. I validate the proposed method's effectiveness by transferring the pre-trained model to multiple action understanding tasks. The results show consistent improvement over the baselines for every task and dataset. To handle the second problem, I formulate human action recognition as an unsupervised learning problem on the target data. In this setting, we have many labeled videos as source data and unlabeled videos as target data. We can use already existing labeled video datasets as source data in this setting. The task is to align the source and target feature distributions so that the learned model can generalize well on the target data. I propose 1) aligning the more important temporal part of each video and 2) encouraging the model to focus on action, not the background scene. The proposed method is simple and intuitive while achieving state-of-the-art performance without training on a lot of labeled target videos. I relax the unsupervised target data setting to a sparsely labeled target data setting. Here, we have many labeled videos as source data and sparsely labeled videos as target data. The setting is practical as sometimes we can afford a little bit of cost for labeling target data. I propose multiple video data augmentation methods to inject color, spatial, temporal, and scene invariances to the action recognition model in this setting. The resulting method shows favorable performance on the public benchmarks.
34
Jacklin, Angela. "The transfer process between special and mainstream schools." Thesis, University of Sussex, 1995. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.296551.
Full text
35
Gustafson, Robert Christian. "An evaluation of forward integration in the transfer conveyor market." Thesis, Massachusetts Institute of Technology, 1994. http://hdl.handle.net/1721.1/12066.
Full text
36
Andersson, Robin. "GPU integration for Deep Learning on YARN." Thesis, KTH, Skolan för informations- och kommunikationsteknik (ICT), 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-222357.
Full textAbstract:
In recent years, there have been many advancements in the field of machine learning and adoption of its techniques in many industries. Deep learning is a sub-field of machine learning that is largely attributed to many of recent innovative applications such as autonomous driving systems. Training a deep learning model is a computationally intensive task that in many cases is inefficient on a CPU. Dramatically faster training can be achieved by making use of one or more GPUs, coupled with the need to train more complex models on increasingly larger datasets, training on a CPU is not sufficient. Hops Hadoop is an Hadoop distribution that aims to make Hadoop more scalable, by migrating the meta-data of YARN and HDFS to MySQL NDB. Hops is currently making efforts to support distributed TensorFlow. However, GPUs are not currently managed natively by YARN, therefore, in Hadoop, GPUs cannot be scheduled to applications. That is, there is no support for isolating GPUs to applications and managing access to applications. This thesis presents an architecture for scheduling and isolating GPUs-as-aresource for Hops Hadoop. In particular, the work is constrained to supporting YARN’s most popular scheduler, the Capacity Scheduler. The architecture is implemented and verified based on a set of test cases. The architecture is evaluated in a quantitative approach by measuring the performance overhead of supporting GPUs by running a set of experiments. The solution piggybacks GPUs during capacity calculation in the sense that GPUs are not included as part of the capacity calculation. The Node Manager makes use of Cgroups to provide exclusive isolation of GPUs to a container. A GPUAllocator component is implemented that keeps an in-memory state of currently available GPU devices and those which are currently allocated locally on the Node Manager. The performance tests concluded that the YARN resource model can be extended with GPUs, and that the overhead is negligible. With our contribution of extending Hops Hadoop to support GPUs as a resource, we are enabling deep learning on Big Data, and making a first step towards support for distributed deep learning.De senaste åren har många framsteg gjorts inom maskininlärning och användning av dess tekniker inom många olika industrier. Djupinlärning är ett delområde inom maskininlärning som är hänförlig till många av de senaste innovativa applikationerna såsom system för autonom bilkörning. Att träna en djupinlärningsmodell är en beräkningsmässigt intensiv uppgift som i många fall är ineffektivt på endast en processor. Dramatiskt snabbare träning är möjlig genom att använda en eller flera grafikkort, kopplat med behov att träna mer komplexa modeller med större datamängder, är det inte hållbart att endast träna på en processor. Hops Hadoop är en Hadoop distribution med målet att göra Hadoop mer skalbart, genom att migrera metadata från YARN och HDFS till MySQL NDB. Hops utför i nuläget ett arbete med att stödja distribuerad TensorFlow. För närvarande finns inget stöd för grafikkort som en resurs i YARN, därmed, i Hadoop, så kan grafikkort inte schemaläggas för applikationer. Mer specifikt, det finns inget stöd för att isolera grafikkort för applikationer och erbjuda som en resurs. Den här uppsatsen presenterar en arkitektur för att schemalägga och isolera grafikkort som en resurs i Hops Hadoop. Arbetet innefattar stöd för den mest populära schemaläggaren i YARN, kapacitets schemaläggaren. Arkitekturen implementeras och verifieras utifrån en mängd testfall. Arkitekturen utvärderas sedan i ett kvantitativt tillvägagångssätt genom att mäta tidspåverkan att stödja grafikkort genom att utföra ett antal experiment. Lösningen tar inte hänsyn till grafikkort som en del av kapacitetsberäkningen. Node Manager komponenten använder Cgroups för att utföra isolering av grafikkort. En GPUAllocator komponent har implementerats som håller ett tillstånd över vilka grafikkort som allokerats och vilka som är lediga på Node Manager. Experimenten konkluderar att YARN kan stödja grafikkort som en resurs och att tidspåverkan för detta är försumbart. Detta arbete med att stödja grafikkort som en resurs på Hops Hadoop, gör det möjligt att utföra djupinlärnin på stora datamängder, och är ett första steg mot stöd för distribuerad djupinlärning.
37
Triantafyllidis, Athanasios. "Increasing eLearning engagement through mobile learning integration." Thesis, University of Plymouth, 2017. http://hdl.handle.net/10026.1/10431.
Full textAbstract:
eLearning applications have penetrated the world of education as most higher education organizations all over the world choose to deploy eLearning applications. A review of literature and surveys performed confirmed that currently there is very little engagement of students in web-based eLearning applications, especially related to web-based constructive activities. In fact, eLearning platforms are mostly used as on-line repositories for a variety of course related documents without actively contributing to the learning process utilizing available modern learning methods. eLearning aims to actively engage students by making available learning content, but also through using interactive practices in the process of learning. Therefore, students in addition to access learning content may actively participate in the discovery of knowledge rather than being passive receptors to that content. Consequently, engagement of students to eLearning activities and content is important. Two surveys were undertaken in order to identify the reasons why web-based eLearning platforms fail to achieve both constructivist learning and the required engagement by both students and instructors. In addition to that, these surveys investigated and measured the level of interactivity of both students and instructors with on-line Information Technology (IT) services offered by both web-based and mobile applications and services. The rational was to investigate opportunities in creating a technology that can disseminate eLearning content that is mainly offered by institutional eLearning platforms and popular on-line services like social networks and communications services, in order to increase awareness, availability, and simplicity of eLearning activities and thus engagement to eLearning. The findings illustrated that most instructors fail to create and promptly support constructive eLearning activities largely because of the complexity and time required for such undertakings. Consequently, the critical student participant mass is not achieved. Additionally, it seems that most learning platforms rely on email messages and native applications’ notifications to update both students and instructors on new interactions. However, these channels of communication are not within the preferred communication channels and thus updates become outdated and fail to serve their purpose. Finally, web-based learning platforms seem to be oriented around laptop/desktop computer use (i.e. a full sized computer screen) rather than adopting and adapting to current mobile use of technology. The research presents a novel conceptual model of a mobile application that integrates and combines various already existing popular, on-line, web-based and mobile application services (communication, social media, voice command systems, etc.) including relative technologies (smart devices, mobile sensors, application servers), with institutional eLearning platforms. The aim is to increase the engagement of both students and instructors to eLearning, through constructive eLearning activities using a variety of existing popular technologies. This research shows that a Mobile Technology Enhanced Learning (mTEL) technology that integrates eLearning activities to both students and instructors will assist in increasing the awareness of learners to eLearning activities. At the same time, it offers the means to access, respond and participate in learning activities virtually from everywhere, thus making interaction ubiquitous, simpler and prompt, thus addressing key eLearning weaknesses leading to low engagement. These benefits are offered to both students and instructors, for a variety of eLearning activities and tools (positivistic and constructive). The research goes one step further by evaluating mTEL’s effectiveness. A conceptual novel model of a mobile application was designed and positively evaluated to contribute in the resolution of the major problem of low engagement of both students and instructors to eLearning. This is achieved by technologically enhancing mobile learning and introducing learning activities and materials at the current, highly populated on-line ecosystems where learners are already engaged instead of expecting them to directly interact with the institutional web-based platforms.
38
Tserendorj, Navchaa, Uranchimeg Tudevdagva, and Ariane Heller. "Integration of Learning Management System into University-level Teaching and Learning." Universitätsbibliothek Chemnitz, 2013. http://nbn-resolving.de/urn:nbn:de:bsz:ch1-qucosa-103595.
Full textAbstract:
With rapid development of science and technology, introduction of the ICT different methodologies into the learning environment today becomes one of the most important factors. Application of IT tools in classroom learning in and methodology for teaching and learning processes creates number of issues, which could be solved with the help of online Learning Management System (LMS).
This paper presents experiment results using of Moodle, at the course of Linear algebra and analytic geometry (LAAG) in the first semester of 2010-2011 and 2011-2012 study year. The paper presents quantitative and qualitative rationale interdependence analysis and experiment conclusion based on midterm and final exam results of the freshman students of the National University of Mongolia.
39
Toll, Debora K. "The transfer of learning: Employees' lived experiences." Thesis, University of Ottawa (Canada), 2004. http://hdl.handle.net/10393/29178.
Full textAbstract:
The employees' ability to continuously and collectively learn, and to apply their learning are critical to their own and their organization's performance. This study, therefore, sought to understand employees' perceptions of and experiences with the application of or, transfer of their learning. It also sought to understand the interplay between the three primary transfer sources. The overarching research question that guided this study was what were employees' lived experiences with transfer? The subquestions were how do employees transfer their learning, when did transfer enter their learning experiences, and why did they believe that transfer occurred? A hermeneutic phenomenological research design was employed. The participants' lived experiences were examined, described and interpreted. By allowing the participants' voices to resonate throughout the text, the depth, richness and meaning of their experiences were captured. Seven federal government employees, at the administrative, professional and managerial levels, comprised the purposeful sample. The participants engaged in a formal audiotaped interview, an informal interview and a focus group session.
Eight main themes emerged from the data analysis. Two themes, related to the individuals' characteristics, were the desire to learn and how transfer occurred. Four themes, related to the training program's design and development features, were discourse, application of the learning to life's situations, learning by doing and when transfer entered the learners' learning experience. The last two themes, related to the organizational climate characteristics, were an open and supportive culture, and the major challenges to transfer. The transfer research, comprised of the individuals' characteristics, training program features and organizational climate characteristics, provided one lens through which the findings were interpreted. Three adult learning theories, self-directed, situated cognition and transformational learning, provided the second lens.
The transfer and adult learning literatures were quite complimentary. The learning theories however, brought a broader and more comprehensive understanding to many of the participants' transfer experiences. The theories, by illuminating the interplay between the primary transfer sources, integrated the quantitative transfer research findings into a more coherent body of knowledge. This research also contributed to a more fullsome understanding of the learning theories and the difficulties in measuring transfer. Adult education principles and practices appear to be well positioned to enhance employees' transfer efforts as transfer does indeed appear to be a key concept in adult learning.
This study advances our understanding of transfer from the perspective of the employees' "lived" experiences, and of the complexities of transfer. The findings are relevant to adult education practices, and to organizations and employees in better understanding and facilitating transfer.
40
Masko, David. "Calibration in Eye Tracking Using Transfer Learning." Thesis, KTH, Skolan för datavetenskap och kommunikation (CSC), 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-210815.
Full textAbstract:
This thesis empirically studies transfer learning as a calibration framework for Convolutional Neural Network (CNN) based appearance-based gaze estimation models. A dataset of approximately 1,900,000 eyestripe images distributed over 1682 subjects is used to train and evaluate several gaze estimation models. Each model is initially trained on the training data resulting in generic gaze models. The models are subsequently calibrated for each test subject, using the subject's calibration data, by applying transfer learning through network fine-tuning on the final layers of the network. Transfer learning is observed to reduce the Euclidean distance error of the generic models within the range of 12-21%, which is in line with current state-of-the-art. The best performing calibrated model shows a mean error of 29.53mm and a median error of 22.77mm. However, calibrating heatmap output-based gaze estimation models decreases the performance over the generic models. It is concluded that transfer learning is a viable calibration framework for improving the performance of CNN-based appearance based gaze estimation models.Detta examensarbete är en empirisk studie på överföringsträning som ramverk för kalibrering av neurala faltningsnätverks (CNN)-baserade bildbaserad blickapproximationsmodeller. En datamängd på omkring 1 900 000 ögonrandsbilder fördelat över 1682 personer används för att träna och bedöma flertalet blickapproximationsmodeller. Varje modell tränas inledningsvis på all träningsdata, vilket resulterar i generiska modeller. Modellerna kalibreras därefter för vardera testperson med testpersonens kalibreringsdata via överföringsträning genom anpassning av de sista lagren av nätverket. Med överföringsträning observeras en minskning av felet mätt som eukilidskt avstånd för de generiska modellerna inom 12-21%, vilket motsvarar de bästa nuvarande modellerna. För den bäst presterande kalibrerade modellen uppmäts medelfelet 29,53mm och medianfelet 22,77mm. Dock leder kalibrering av regionella sannolikhetsbaserade blickapproximationsmodeller till en försämring av prestanda jämfört med de generiska modellerna. Slutsatsen är att överföringsträning är en legitim kalibreringsansats för att förbättra prestanda hos CNN-baserade bildbaserad blickapproximationsmodeller.
41
Maehle, Valerie A. "Conceptual models in the transfer of learning." Thesis, University of Aberdeen, 1993. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.261454.
Full textAbstract:
In order to attain clinical competence student physiotherapists apply knowledge from a range of cognitive domains in the assessment and treatment of patients with a variety of conditions. Current research indicates that the ability to transfer knowledge to a wide variety of conditions requires a cognitive structure in which concepts are embedded in a rich network of interconnections (Faletti, 1990, Spiro, 1987). A concept mapping technique was selected as means of eliciting a representation of the knowledge the student possessed and would access in order to underpin the assessment and treatment of a specific peripheral joint condition. Twenty second and third year physiotherapy students currently on clinical placement in an Out-Patient Department each produced a concept map prior to assessing the patient. A modification of the 'Student Teacher Dialogue' (Hammond et al, 1989) was the methodology selected for identification of the transfer of learning. Analysis of the transcription of this interaction provided evidence of the domain specific and procedural knowledge transferred to the patient assessment. Weak correlations were found to exist between the degree of complexity of the concept map the student produced and the amount and level of transfer achieved in the clinical setting. Also there was evidence to suggest that abstract subject areas, or those which involved practical or clinical applications, facilitated the development of more concentrated conceptual networks. However, contrary to expectation, third year students failed to produce higher quality maps than second year students, despite having greater academic and clinical experience.
42
Kodirov, Elyor. "Cross-class transfer learning for visual data." Thesis, Queen Mary, University of London, 2017. http://qmro.qmul.ac.uk/xmlui/handle/123456789/31852.
Full textAbstract:
Automatic analysis of visual data is a key objective of computer vision research; and performing visual recognition of objects from images is one of the most important steps towards understanding and gaining insights into the visual data. Most existing approaches in the literature for the visual recognition are based on a supervised learning paradigm. Unfortunately, they require a large amount of labelled training data which severely limits their scalability. On the other hand, recognition is instantaneous and effortless for humans. They can recognise a new object without seeing any visual samples by just knowing the description of it, leveraging similarities between the description of the new object and previously learned concepts. Motivated by humans recognition ability, this thesis proposes novel approaches to tackle cross-class transfer learning (crossclass recognition) problem whose goal is to learn a model from seen classes (those with labelled training samples) that can generalise to unseen classes (those with labelled testing samples) without any training data i.e., seen and unseen classes are disjoint. Specifically, the thesis studies and develops new methods for addressing three variants of the cross-class transfer learning: Chapter 3 The first variant is transductive cross-class transfer learning, meaning labelled training set and unlabelled test set are available for model learning. Considering training set as the source domain and test set as the target domain, a typical cross-class transfer learning assumes that the source and target domains share a common semantic space, where visual feature vector extracted from an image can be embedded using an embedding function. Existing approaches learn this function from the source domain and apply it without adaptation to the target one. They are therefore prone to the domain shift problem i.e., the embedding function is only concerned with predicting the training seen class semantic representation in the learning stage during learning, when applied to the test data it may underperform. In this thesis, a novel cross-class transfer learning (CCTL) method is proposed based on unsupervised domain adaptation. Specifically, a novel regularised dictionary learning framework is formulated by which the target class labels are used to regularise the learned target domain embeddings thus effectively overcoming the projection domain shift problem. Chapter 4 The second variant is inductive cross-class transfer learning, that is, only training set is assumed to be available during model learning, resulting in a harder challenge compared to the previous one. Nevertheless, this setting reflects a real-world setting in which test data is available after the model learning. The main problem remains the same as the previous variant, that is, the domain shift problem occurs when the model learned only from the training set is applied to the test set without adaptation. In this thesis, a semantic autoencoder (SAE) is proposed building on an encoder-decoder paradigm. Specifically, first a semantic space is defined so that knowledge transfer is possible from the seen classes to the unseen classes. Then, an encoder aims to embed/project a visual feature vector into the semantic space. However, the decoder exerts a generative task, that is, the projection must be able to reconstruct the original visual features. The generative task forces the encoder to preserve richer information, thus the learned encoder from seen classes is able generalise better to the new unseen classes. Chapter 5 The third one is unsupervised cross-class transfer learning. In this variant, no supervision is available for model learning i.e., only unlabelled training data is available, leading to the hardest setting compared to the previous cases. The goal, however, is the same, learning some knowledge from the training data that can be transferred to the test data composed of completely different labels from that of training data. The thesis proposes a novel approach which requires no labelled training data yet is able to capture discriminative information. The proposed model is based on a new graph regularised dictionary learning algorithm. By introducing a l1- norm graph regularisation term, instead of the conventional squared l2-norm, the model is robust against outliers and noises typical in visual data. Importantly, the graph and representation are learned jointly, resulting in further alleviation of the effects of data outliers. As an application, person re-identification is considered for this variant in this thesis.
43
Boyer, Sebastien (Sebastien Arcario). "Transfer learning for predictive models in MOOCs." Thesis, Massachusetts Institute of Technology, 2016. http://hdl.handle.net/1721.1/104832.
Full textAbstract:
Thesis: S.M. in Technology and Policy, Massachusetts Institute of Technology, School of Engineering, Institute for Data, Systems, and Society, Technology and Policy Program, 2016.Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2016.
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 85-87).
Predictive models are crucial in enabling the personalization of student experiences in Massive Open Online Courses. For successful real-time interventions, these models must be transferable - that is, they must perform well on a new course from a different discipline, a different context, or even a different MOOC platform. In this thesis, we first investigate whether predictive models "transfer" well to new courses. We then create a framework to evaluate the "transferability" of predictive models. We present methods for overcoming the biases introduced by specific courses into the models by leveraging a multi-course ensemble of models. Using 5 courses from edX, we show a predictive model that, when tested on a new course, achieved up to a 6% increase in AUCROC across 90 different prediction problems. We then tested this model on 10 courses from Coursera (a different platform) and demonstrate that this model achieves an AUCROC of 0.8 across these courses for the problem of predicting dropout one week in advance. Thus, the model "transfers" very well.
by Sebastien Boyer.
S.M. in Technology and Policy
S.M.
44
Scahill, Victoria Louise. "Perceptual learning and transfer along a continuum." Thesis, University of Cambridge, 2002. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.620585.
Full text
45
Grönlund, Lucas. "Transfer learning in Swedish - Twitter sentiment classification." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-252536.
Full textAbstract:
Language models can be applied to a diverse set of tasks with great results, but training a language model can unfortunately be a costly task, both in time and money. By transferring knowledge from one domain to another, the costly training only has to be performed once, thus opening the door for more applications. Most current research is carried out with English as the language of choice, thus limiting the amount of available already trained language models in other languages. This thesis explores how the amount of data available for training a language model effects the performance on a Twitter sentiment classification task, and was carried out using Swedish as the language of choice. The Swedish Wikipedia was used as a source for pre-training the language models which were then transferred over to a domain consisting of Swedish tweets. Several models were trained using different amounts of data from these two domains in order to compare the performance of these models. The results of the model evaluation shows that transferring knowledge from the Swedish Wikipedia to tweets yield little to no improvements, while unsupervised fine-tuning on tweets give raise to large improvements in performance.Språkmodeller kan appliceras på en mängd olika uppgifter med bra resultat, men att träna en språkmodell kan dessvärre vara kostsamt både tids- och pengamässigt. Genom att överföra information från en domän till en annan behöver denna kostsamma träningsprocess bara genomföras en gång, och ger således lättare tillgång till dessa modeller. Dagens forskning genomförs främst med engelska som språk vilket således begränsar mängden av färdigtränade modeller på andra språk. Denna rapport utforskar hur mängden data tillgänglig för träning av språkmodeller påverkar resultatet i ett problem gällande attitydanalys av tweets, och utfördes med svenska som språk. Svenska Wikipedia användes för att först träna språkmodellerna som sedan överfördes till en domän bestående av tweets på svenska. Ett flertal språkmodeller tränades med olika mängd data från dessa två domäner för att sedan kunna jämföra deras prestanda. Resultaten visar att överföring av kunskap från Wikipedia till tweets knappt gav upphov till någon förbättring, medan oövervakad träning på tweets förbättrade resultaten markant.
46
Pang, Jinyong. "Human Activity Recognition Based on Transfer Learning." Scholar Commons, 2018. https://scholarcommons.usf.edu/etd/7558.
Full textAbstract:
Human activity recognition (HAR) based on time series data is the problem of classifying various patterns. Its widely applications in health care owns huge commercial benefit. With the increasing spread of smart devices, people have strong desires of customizing services or product adaptive to their features. Deep learning models could handle HAR tasks with a satisfied result. However, training a deep learning model has to consume lots of time and computation resource. Consequently, developing a HAR system effectively becomes a challenging task. In this study, we develop a solid HAR system using Convolutional Neural Network based on transfer learning, which can eliminate those barriers.
47
Broqvist, Widham Emil. "Scaling up Maximum Entropy Deep Inverse Reinforcement Learning with Transfer Learning." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-281796.
Full textAbstract:
In this thesis an issue with common inverse reinforcement learning algorithms is identified, which causes them to be computationally heavy. A solution is proposed which attempts to address this issue and which can be built upon in the future. The complexity of inverse reinforcement algorithms is increased because at each iteration something called a reinforcement learning step is performed to evaluate the result of the previous iteration and guide future learning. This step is slow to perform for problems with large state spaces and where many iterations are required. It has been observed that the problem solved in this step in many cases is very similar to that of the previous iteration. Therefore the solution suggested is to utilize transfer learning to retain some of the learned information and improve speed at subsequent steps. In this thesis different forms of transfers are evaluated for common reinforcement learning algorithms when applied to this problem. Experiments are run using value iteration and Q-learning as the algorithms for the reinforcement learning step. The algorithms are applied to two route planning problems and it is found that in both cases a transfer can be useful for improving calculation times. For value iteration the transfer is easy to understand and implement and shows large improvements in speed compared to the basic method. For Q-learning the implementation contains more variables and while it shows an improvement it is not as dramatic as that for value iteration. The conclusion drawn is that for inverse reinforcement learning implementations using value iteration a transfer is always recommended while for implementations using other algorithms for the reinforcement learning step a transfer is most likely recommended but more experimentation needs to be conducted.I denna uppsats identifieras ett vanligt problem med algoritmer för omvänd förstärkt inlärning vilket leder till att de blir beräkningstunga. En lösning föreslås som försöker addressera problemet och som kan byggas på i framtiden. Komplexiteten i algoritmer för omvänd förstärkt inlärning ökar på grund av att varje iteration kräver ett så kallat förstärkt inlärnings-steg som har som syfte att utvärdera föregående iteration och guida lärandet. Detta steg tar lång tid att genomföra för problem med stor tillståndsrymd och där många iterationer är nödvändiga. Det har observerats att problemet som löses i detta steg i många fall är väldigt likt det problem som löstes i föregående iteration. Därför är den föreslagna lösningen att använda sig av informationsöverföring för att ta tillvara denna kunskap. I denna uppsats utvärderas olika former av informationsöverföring för vanliga algoritmer för förstärkt inlärning på detta problem. Experiment görs med value iteration och Q-learning som algoritmerna för förstärkt inlärnings-steget. Algoritmerna appliceras på två ruttplanneringsproblem och finner att i båda fallen kan en informationsöverföring förbättra beräkningstider. För value iteration är överföringen enkel att implementera och förstå och visar stora förbättringar i hastighet jämfört med basfallet. För Qlearning har implementationen fler variabler och samtidigt som en förbättring visas så är den inte lika dramatisk som för value iteration. Slutsaterna som dras är att för implementationer av omvänd förstärkt inlärning där value iteration används som algoritm för förstärkt inlärnings-steget så rekommenderas alltid en informationsöverföring medan för implementationer som använder andra algoritmer så rekommenderas troligtvis en överföring men fler experiment skulle behöva utföras.
48
Juozapaitis, Jeffrey James. "Exploring Supervised Many Layered Learning as a Precursor to Transfer Learning." Thesis, The University of Arizona, 2012. http://hdl.handle.net/10150/271607.
Full textAbstract:
In this paper, we learn a simple conceptual card game as learned by David Stracuzzi's Cumulus algorithm. We then posit a (sadly unimplemented) scheme to transfer the neural net created by it to a similar game with small modifications, hopefully cutting down the learning time. We then analyze the flaws with the transfer scheme and posit other schemes that may produce better results.
49
Svensson, Carl. "Automatic Log Analysis System Integration : Message Bus Integration in a Machine Learning Environment." Thesis, KTH, Radio Systems Laboratory (RS Lab), 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-168837.
Full textAbstract:
Ericsson is one of the world's largest providers of communications technology and services. Reliable networks are important to deliver services that live up to customers' expectations. Tests are frequently run on Ericsson's systems in order to identify stability problems in their networks. These tests are not always completely reliable. The logs produced by these tests are gathered and analyzed to identify abnormal system behavior, especially abnormal behavior that the tests might not have caught. To automate this analysis process, a machine learning system, called the Awesome Automatic Log Analysis Application (AALAA), is used at Ericsson's Continuous Integration Infrastructure (CII)-department to identify problems within the large logs produced by automated Radio Base Station test loops and processes. AALAA is currently operable in two versions using different distributed cluster computing platforms: Apache Spark and Apache Hadoop. However, it needs improvements in its machine-to-machine communication to make this process more convenient to use. In this thesis, message communication has successfully been implemented in the AALAA system. The result is a message bus deployed in RabbitMQ that is able to successfully initiate model training and abnormal log identification through requests, and to handle a continuous flow of result updates from AALAA.Ericsson är en av världens största leverantörer av kommunikationsteknologi och tjänster. Tillförlitliga nätverk är viktigt att tillhandahålla för att kunna leverera tjänster som lever upp till kundernas förväntningar. Tester körs därför ofta i Ericssons system med syfte att identifiera stabilitetsproblem som kan uppstå i nätverken. Dessa tester är inte alltid helt tillförlitliga, producerade testloggar samlas därför in och analyseras för att kunna identifiera onormalt beteende som testerna inte lyckats hitta. För att automatisera denna analysprocess har ett maskininlärningssystem utvecklats, Awesome Automatic Log Analysis Application (AALAA). Detta system används i Ericssons Continuous Integration Infrastructure (CII)-avdelning för att identifiera problem i stora loggar som producerats av automatiserade Radio Base Station tester. AALAA är för närvarande funktionellt i två olika versioner av distribuerad klusterberäkning, Apache Spark och Apache Hadoop, men behöver förbättringar i sin maskin-till-maskin-kommunikation för att göra dem enklare och effektivare att använda. I denna avhandling har meddelandekommunikation implementerats som kan kommunicera med flera olika moduler i AALAA. Resultatet är en meddelandebuss implementerad i RabbitMQ som kan initiera träning av modeller och identifiering av onormala loggar på begäran, samt hantera ett kontinuerligt flöde av resultatuppdateringar från pågående beräkningar.
50
McHone, Cheryl. "Blended Learning Integration: Student Motivation and Autonomy in a Blended Learning Environment." Digital Commons @ East Tennessee State University, 2020. https://dc.etsu.edu/etd/3750.
Full textAbstract:
The purpose of this study was to analyze teacher perceptions on the relationship of technology and student academic behaviors and performance in the blended learning environment across 9th through 12th grade within east Tennessee and to identify the components of blended learning and pedagogical practices that enhance students’ academic behaviors. Specifically, this study is an analysis of how student motivation and student autonomy relate to technology implementation and face-to-face instruction within blended learning environments.
The participants of this study were teachers within 2 school districts in East Tennessee. All high school teachers within the participating school districts received an online survey that was distributed from their corresponding principals via email. The online survey used a Likert-type scale that consisted of 40 items focused on teachers’ perceptions of student motivation and student autonomy with the blended learning environment. The analysis of the data was based on the responses of 75 teachers from the 2 participating school districts.
Statistical analyses of the data revealed that the amount of teacher technology use, student technology use, learning management system use, and type of professional development did not have a significant relationship with participants’ perspective of student motivation or student autonomy. The research also did not reveal a significant relationship between participants’ age and perception of student motivation. However, this research revealed a significant relationship between participant age and participants’ perception of student autonomy. The study revealed that, as participant age increased, participants’ mean student autonomy scores decreased.