Academic literature on the topic 'Novel task transfer'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Novel task transfer.'
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.
Journal articles on the topic "Novel task transfer"
1
Vincent, Vercruyssen, Meert Wannes, and Davis Jesse. "Transfer Learning for Anomaly Detection through Localized and Unsupervised Instance Selection." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (April 3, 2020): 6054–61. http://dx.doi.org/10.1609/aaai.v34i04.6068.
Full textAbstract:
Anomaly detection attempts to identify instances that deviate from expected behavior. Constructing performant anomaly detectors on real-world problems often requires some labeled data, which can be difficult and costly to obtain. However, often one considers multiple, related anomaly detection tasks. Therefore, it may be possible to transfer labeled instances from a related anomaly detection task to the problem at hand. This paper proposes a novel transfer learning algorithm for anomaly detection that selects and transfers relevant labeled instances from a source anomaly detection task to a target one. Then, it classifies target instances using a novel semi-supervised nearest-neighbors technique that considers both unlabeled target and transferred, labeled source instances. The algorithm outperforms a multitude of state-of-the-art transfer learning methods and unsupervised anomaly detection methods on a large benchmark. Furthermore, it outperforms its rivals on a real-world task of detecting anomalous water usage in retail stores.
2
Kearney, Philip E., and Phil Judge. "Successful Transfer of a Motor Learning Strategy to a Novel Sport." Perceptual and Motor Skills 124, no. 5 (July 7, 2017): 1009–21. http://dx.doi.org/10.1177/0031512517719189.
Full textAbstract:
This study investigated whether secondary school students who were taught a motor learning strategy could transfer their knowledge of the strategy to learning a novel task. Twenty adolescents were randomly allocated to a strategy or control group. The strategy group was taught Singer’s five-step learning strategy, while the control group received information on the evolution and biomechanics of the basketball free throw. Both groups received three 1-hour practice sessions on a modified basketball shooting task. After one month, participants were introduced to the transfer task, golf putting. Performance accuracy was recorded for all tasks, and participants completed questionnaires regarding strategy use during practice. Participants taught the five-step learning strategy successfully recalled and applied it after a 1-month interval, and they demonstrated superior performance on both acquisition and transfer tasks, relative to the control group. Physical education teachers and coaches should consider using this learning strategy to enhance the learning of closed motor skills.
3
Catrambone, Richard. "Specific versus General Instructions: Initial Performance and Later Transfer." Proceedings of the Human Factors Society Annual Meeting 33, no. 19 (October 1989): 1320–23. http://dx.doi.org/10.1177/154193128903301918.
Full textAbstract:
Two experiments demonstrated that people who receive specific instructions (SI subjects) for using a word processor are able to accomplish initial tasks more quickly than people who receive more general instructions (GI subjects). Experiment 1 found, however, that SI subjects were unable to do a novel transfer task unless they received hints while GI subjects had no trouble with the transfer task. A production rule analysis was used to guide a revision of the specific instructions so that those instructions promoted generalization. Experiment 2 used these revised specific instructions and found that SI subjects were now able to do a novel transfer task about as well as GI subjects. These results suggest that a production system is a useful tool for analyzing instructions and predicting user performance and that specific instructions designed to promote generalization may be the most effective type of instructions.
4
GARCÍA, ESTEBAN O., ENRIQUE MUNOZ DE COTE, and EDUARDO F. MORALES. "TRANSFER LEARNING FOR CONTINUOUS STATE AND ACTION SPACES." International Journal of Pattern Recognition and Artificial Intelligence 28, no. 07 (October 14, 2014): 1460007. http://dx.doi.org/10.1142/s0218001414600076.
Full textAbstract:
Transfer learning focuses on developing methods to reuse information gathered from a source task in order to improve the learning performance in a related task. In this work, we present a novel approach to transfer knowledge between tasks in a reinforcement learning (RL) framework with continuous states and actions, where the transition and policy functions are approximated by Gaussian processes. The novelty in the proposed approach lies in the idea of transferring information about the hyper-parameters of the state transition function from the source task, which represents qualitative knowledge about the type of transition function that the target task might have, constraining the search space and accelerating the learning process. We performed experiments on relevant tasks for RL, which show a clear improvement in the overall performance when compared to state-of-the-art reinforcement learning and transfer learning algorithms for continuous state and action spaces.
5
Kono, Hitoshi, Yuto Sakamoto, Yonghoon Ji, and Hiromitsu Fujii. "Automatic Transfer Rate Adjustment for Transfer Reinforcement Learning." International Journal of Artificial Intelligence & Applications 11, no. 6 (November 30, 2020): 47–54. http://dx.doi.org/10.5121/ijaia.2020.11605.
Full textAbstract:
This paper proposes a novel parameter for transfer reinforcement learning to avoid over-fitting when an agent uses a transferred policy from a source task. Learning robot systems have recently been studied for many applications, such as home robots, communication robots, and warehouse robots. However, if the agent reuses the knowledge that has been sufficiently learned in the source task, deadlock may occur and appropriate transfer learning may not be realized. In the previous work, a parameter called transfer rate was proposed to adjust the ratio of transfer, and its contribution include avoiding dead lock in the target task. However, adjusting the parameter depends on human intuition and experiences. Furthermore, the method for deciding transfer rate has not discussed. Therefore, an automatic method for adjusting the transfer rate is proposed in this paper using a sigmoid function. Further, computer simulations are used to evaluate the effectiveness of the proposed method to improve the environmental adaptation performance in a target task, which refers to the situation of reusing knowledge.
6
Abdelrahman, Amro M., Denny Yu, Bethany R. Lowndes, EeeLN H. Buckarma, Becca L. Gas, David R. Farley, Juliane Bingener, and M. Susan Hallbeck. "Validation of a Novel Inverted Peg Transfer Task: Advancing Beyond the Regular Peg Transfer Task for Surgical Simulation-Based Assessment." Journal of Surgical Education 75, no. 3 (May 2018): 836–43. http://dx.doi.org/10.1016/j.jsurg.2017.09.028.
Full text
7
Lei, Feifei, Jieren Cheng, Yue Yang, Xiangyan Tang, Victor S. Sheng, and Chunzao Huang. "Improving Heterogeneous Network Knowledge Transfer Based on the Principle of Generative Adversarial." Electronics 10, no. 13 (June 24, 2021): 1525. http://dx.doi.org/10.3390/electronics10131525.
Full textAbstract:
Deep learning requires a large amount of datasets to train deep neural network models for specific tasks, and thus training of a new model is a very costly task. Research on transfer networks used to reduce training costs will be the next turning point in deep learning research. The use of source task models to help reduce the training costs of the target task models, especially heterogeneous systems, is a problem we are studying. In order to quickly obtain an excellent target task model driven by the source task model, we propose a novel transfer learning approach. The model linearly transforms the feature mapping of the target domain and increases the weight value for feature matching to realize the knowledge transfer between heterogeneous networks and add a domain discriminator based on the principle of generative adversarial to speed up feature mapping and learning. Most importantly, this paper proposes a new objective function optimization scheme to complete the model training. It successfully combines the generative adversarial network with the weight feature matching method to ensure that the target model learns the most beneficial features from the source domain for its task. Compared with the previous transfer algorithm, our training results are excellent under the same benchmark for image recognition tasks.
8
Jing, Mingxuan, Xiaojian Ma, Wenbing Huang, Fuchun Sun, and Huaping Liu. "Task Transfer by Preference-Based Cost Learning." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 2471–78. http://dx.doi.org/10.1609/aaai.v33i01.33012471.
Full textAbstract:
The goal of task transfer in reinforcement learning is migrating the action policy of an agent to the target task from the source task. Given their successes on robotic action planning, current methods mostly rely on two requirements: exactlyrelevant expert demonstrations or the explicitly-coded cost function on target task, both of which, however, are inconvenient to obtain in practice. In this paper, we relax these two strong conditions by developing a novel task transfer framework where the expert preference is applied as a guidance. In particular, we alternate the following two steps: Firstly, letting experts apply pre-defined preference rules to select related expert demonstrates for the target task. Secondly, based on the selection result, we learn the target cost function and trajectory distribution simultaneously via enhanced Adversarial MaxEnt IRL and generate more trajectories by the learned target distribution for the next preference selection. The theoretical analysis on the distribution learning and convergence of the proposed algorithm are provided. Extensive simulations on several benchmarks have been conducted for further verifying the effectiveness of the proposed method.
9
Toader, Andra F., and Thomas Kessler. "Task Variation and Mental Models Divergence Influencing the Transfer of Team Learning." Small Group Research 49, no. 5 (July 26, 2018): 545–75. http://dx.doi.org/10.1177/1046496418786429.
Full textAbstract:
We investigate how teams develop and transfer general problem-solving skills across two ill-structured problems. We draw on cognitive flexibility theory in the instructional literature and propose that teams will achieve a higher performance on a novel task or transfer when they receive an external task intervention (i.e., task variation) and when the internal mechanisms (i.e., divergent mental models) are developed to make sense of the external intervention. To test these predictions, we designed a longitudinal experiment with 17 student teams that encountered task variation during their work on an initial task. Consistent with our predictions, we found that teams that experienced variations and whose mental models diverged during their work on an initial task achieved higher performance on a novel task than teams that experienced variation and whose mental models converged. Implications for the transfer of learning in teams on ill-structured problems are discussed.
10
Vandenbroucke, B., and P. Camps. "CMACIONIZE 2.0: a novel task-based approach to Monte Carlo radiation transfer." Astronomy & Astrophysics 641 (September 2020): A66. http://dx.doi.org/10.1051/0004-6361/202038364.
Full textAbstract:
Context. Monte Carlo radiative transfer (MCRT) is a widely used technique to model the interaction between radiation and a medium. It plays an important role in astrophysical modelling and when these models are compared with observations. Aims. We present a novel approach to MCRT that addresses the challenging memory-access patterns of traditional MCRT algorithms, which prevent an optimal performance of MCRT simulations on modern hardware with a complex memory architecture. Methods. We reformulated the MCRT photon-packet life cycle as a task-based algorithm, whereby the computation is broken down into small tasks that are executed concurrently. Photon packets are stored in intermediate buffers, and tasks propagate photon packets through small parts of the computational domain, moving them from one buffer to another in the process. Results. Using the implementation of the new algorithm in the photoionization MCRT code CMACIONIZE 2.0, we show that the decomposition of the MCRT grid into small parts leads to a significant performance gain during the photon-packet propagation phase, which constitutes the bulk of an MCRT algorithm because memory caches are used more efficiently. Our new algorithm is faster by a factor 2 to 4 than an equivalent traditional algorithm and shows good strong scaling up to 30 threads. We briefly discuss adjustments to our new algorithm and extensions to other astrophysical MCRT applications. Conclusions. We show that optimising the memory access patterns of a memory-bound algorithm such as MCRT can yield significant performance gains.
Dissertations / Theses on the topic "Novel task transfer"
1
Wrathall, Stephen, and res cand@acu edu au. "The Effects of Contextual Interference and Variability of Practice on the Acquisition of a Motor Task and Transfer to a Novel Task." Australian Catholic University. School of Exercise Science, 2004. http://dlibrary.acu.edu.au/digitaltheses/public/adt-acuvp63.29082005.
Full textAbstract:
AIM The purpose of this experiment is to assess whether the advantages of variable practice are due to schema formation or to enhanced information processing (contextual interference) alone. DESIGN The design involved a 2 (mode; cognitive and motor) x 5 (practice schedule; blocked, random, constant distance one, constant distance two, and constant distance three) between subjects design resulting in ten groups. One hundred participants were randomly chosen from Human Movement students at Australian Catholic University and assigned to each of the ten groups (n=10). The cognitive mode involved the participants having to recognise the appropriate target from three geometrical shapes (triangle, square or circle), the triangle being the target in every case. The motor mode involved the participants having to tap on the target among three boxes that was merely filled in. The experiment consisted of ninety (3 blocks of 30) acquisition trials followed by ten transfer trials to a novel movement. MAIN HYPOTHESIS It was hypothesised that if facilitated transfer to a novel target occurs through schema formation, then there would be no differences between the motor groups and their corresponding cognitive groups. However, if facilitated transfer to a novel target occurs through enhanced information processing, then there would be differences between the motor groups and their corresponding cognitive groups. RESULTS Statistical analysis revealed a contextual interference effect for participants involved in the cognitive mode, in that the cognitive blocked group outperformed the cognitive random group in acquisition, but the reverse was the case in transfer. In the motor mode, the motor blocked group outperformed the motor random group in acquisition, and repeated the performance in transfer. CONCLUSION The results appear to indicate that for simple motor tasks it is the amount of variability of practice that is important for transfer to a novel task, while for tasks with a cognitive component, the schedule of practice is critical.
2
Ye, Meng. "VISUAL AND SEMANTIC KNOWLEDGE TRANSFER FOR NOVEL TASKS." Diss., Temple University Libraries, 2019. http://cdm16002.contentdm.oclc.org/cdm/ref/collection/p245801coll10/id/583037.
Full textAbstract:
Computer and Information SciencePh.D.
Data is a critical component in a supervised machine learning system. Many successful applications of learning systems on various tasks are based on a large amount of labeled data. For example, deep convolutional neural networks have surpassed human performance on ImageNet classification, which consists of millions of labeled images. However, one challenge in conventional supervised learning systems is their generalization ability. Once a model is trained on a specific dataset, it can only perform the task on those \emph{seen} classes and cannot be used for novel \emph{unseen} classes. In order to make the model work on new classes, one has to collect and label new data and then re-train the model. However, collecting data and labeling them is labor-intensive and costly, in some cases, it is even impossible. Also, there is an enormous amount of different tasks in the real world. It is not applicable to create a dataset for each of them. These problems raise the need for Transfer Learning, which is aimed at using data from the \emph{source} domain to improve the performance of a model on the \emph{target} domain, and these two domains have different data or different tasks. One specific case of transfer learning is Zero-Shot Learning. It deals with the situation where \emph{source} domain and \emph{target} domain have the same data distribution but do not have the same set of classes. For example, a model is given animal images of `cat' and `dog' for training and will be tested on classifying 'tiger' and 'wolf' images, which it has never seen. Different from conventional supervised learning, Zero-Shot Learning does not require training data in the \emph{target} domain to perform classification. This property gives ZSL the potential to be broadly applied in various applications where a system is expected to tackle unexpected situations. In this dissertation, we develop algorithms that can help a model effectively transfer visual and semantic knowledge learned from \emph{source} task to \emph{target} task. More specifically, first we develop a model that learns a uniform visual representation of semantic attributes, which help alleviate the domain shift problem in Zero-Shot Learning. Second, we develop an ensemble network architecture with a progressive training scheme, which transfers \emph{source} domain knowledge to the \emph{target} domain in an end-to-end manner. Lastly, we move a step beyond ZSL and explore Label-less Classification, which transfers knowledge from pre-trained object detectors into scene classification tasks. Our label-less classification takes advantage of word embeddings trained from unorganized online text, thus eliminating the need for expert-defined semantic attributes for each class. Through comprehensive experiments, we show that the proposed methods can effectively transfer visual and semantic knowledge between tasks, and achieve state-of-the-art performances on standard datasets.
Temple University--Theses
3
Chan, Sharon. "Far-transfer effects of working memory training on a novel problem solving task." Thesis, 2014. http://hdl.handle.net/1828/5508.
Full textAbstract:
The goal of this study is to assess the far-transfer effects of strategy-based working
memory (WM) training to a novel problem solving task. Far-transfer refers to the application of
trained skills to an untrained situation and is especially important because it deals with the
generalization of learning to novel contexts. However, previous working memory training
studies have produced little evidence for far-transfer. In the current study, children were trained
in two strategies, phonological rehearsal and semantic categorization. These strategies have been
suggested to increase the efficiency in processing and encoding of information and are invoked
to explain developmental increases in WM capacity. Sixteen 6-to 9-year-olds were randomly
assigned to each of four training conditions: semantic and rehearsal training, semantic training
only, rehearsal training only, and treated control group. The treated control group performed
significantly worse on the problem solving task compared to the three training groups.
Surprisingly, the treatment groups did not differ significantly from each other. There was no
statistically significant difference in receiving combined training of both strategies compared to
only one strategy and furthermore, neither strategy resulted in better performance compared to
the other strategy. Future directions for WM training and the implications for cognitive
interventions are discussed.Graduate
0620
0633
sharonc@uvic.ca
Books on the topic "Novel task transfer"
1
Akande, Dapo, Jaakko Kuosmanen, Helen McDermott, and Dominic Roser, eds. Human Rights and 21st Century Challenges. Oxford University Press, 2020. http://dx.doi.org/10.1093/oso/9780198824770.001.0001.
Full textAbstract:
The world faces significant and interrelated challenges in the twenty-first century which threaten human rights in a number of ways. This book examines the relationship between human rights and three of the largest challenges of the twenty-first century: conflict and security, environment, and poverty. Technological advances in fighting wars have led to the introduction of new weapons which threaten to transform the very nature of conflict. In addition, states confront threats to security which arise from a new set of international actors not clearly defined and which operate globally. Climate change, with its potentially catastrophic impacts, features a combination of characteristics which are novel for humanity. The problem is caused by the sum of innumerable individual actions across the globe and over time, and similarly involves risks that are geographically and temporally diffuse. In recent decades, the challenges involved in addressing global and national poverty have also changed. For example, the relative share of the poor in the world population has decreased significantly while the relative share of the poor who live in countries with significant domestic capacity has increased strongly. Overcoming these global and interlocking threats constitutes this century’s core political and moral task. This book examines how these challenges may be addressed using a human rights framework. It considers how these challenges threaten human rights and seeks to reassess our understanding of human rights in the light of these challenges. The analysis considers both foundational and applied questions. The approach is multidisciplinary and contributors include some of the most prominent lawyers, philosophers, and political theorists in the debate. The authors not only include leading academics but also those who have played important roles in shaping the policy debates on these questions. Each Part includes contributions by those who have served as Special Rapporteurs within the United Nations human rights system on the challenges under consideration.
Book chapters on the topic "Novel task transfer"
1
Al-Habaibeh, Amin, Ampea Boateng, and Hyunjoo Lee. "Innovative Strategy for Addressing the Challenges of Monitoring Off-Shore Wind Turbines for Condition-Based Maintenance." In Springer Proceedings in Energy, 189–96. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-63916-7_24.
Full textAbstract:
AbstractOff-shore wind energy technology is considered to be one of the most important renewable energy source in the 21st century towards reducing carbon emission and providing the electricity needed to power our cities. However, due to being installed away from the shore, ensuring availability and performing maintenance procedures could be an expensive and time consuming task. Condition Based Maintenance (CBM) could play an important role in enhancing the payback period on investment and avoiding unexpected failures that could reduce the available capacity and increase maintenance costs. Due to being at distance from the shore, it is difficult to transfer high frequency data in real time and because of this data transferring issue, only low frequency-average SCADA data (Supervisory Control And Data Acquisition) is available for condition monitoring. Another problem when monitoring wind energy is the massive variation in weather conditions (e.g. wind speed and direction), which could produce a wide range of operational alerts and warnings. This paper presents a novel case study of integrated event-based wind turbine alerts with time-based sensory data from the SCADA system to perform a condition monitoring strategy to categorise health conditions. The initial results presented in this paper, using vibration levels of the drive train, indicate that the suggested monitoring strategy could be implemented to develop an effective condition monitoring system.
2
Passingham, Richard E. "Prefrontal Cortex." In Understanding the Prefrontal Cortex, 287–330. Oxford University Press, 2021. http://dx.doi.org/10.1093/oso/9780198844570.003.0008.
Full textAbstract:
The key to the granular prefrontal (PF) cortex is that it sits at the top of the sensory processing hierarchy, the motor hierarchy, and the outcome hierarchy. This means that it is a position to learn abstract task rules. These relate to conditional tasks that involve sequences, associations, and attentional performance. Because they can learn abstract rules, primates can show specific behavioural transfer from one problem to another when the problems share the same logic. And, since the different PF areas are closely interconnected, the PF cortex provides a general-purpose mechanism for the rapid solution of novel tasks.
3
Duy, Phan The, Nghi Hoang Khoa, Hoang Hiep, Nguyen Ba Tuan, Hien Do Hoang, Do Thi Thu Hien, and Van-Hau Pham. "A Deep Transfer Learning Approach for Flow-Based Intrusion Detection in SDN-Enabled Network." In Frontiers in Artificial Intelligence and Applications. IOS Press, 2021. http://dx.doi.org/10.3233/faia210031.
Full textAbstract:
Revolutionizing operation model of traditional network in programmability, scalability, and orchestration, Software-Defined Networking (SDN) has considered as a novel network management approach for a massive network with heterogeneous devices. However, it is also highly susceptible to security attacks like conventional network. Inspired from the success of different machine learning algorithms in other domains, many intrusion detection systems (IDS) are presented to identify attacks aiming to harm the network. In this paper, leveraging the flow-based nature of SDN, we introduce DeepFlowIDS, a deep learning (DL)-based approach for anomaly detection using the flow analysis method in SDN. Furthermore, instead of using a lot of network properties, we only utilize essential characteristics of traffic flows to analyze with deep neural networks in IDS. This is to reduce the computational and time cost of attack traffic detection. Besides, we also study the practical benefits of applying deep transfer learning from computer vision to intrusion detection. This method can inherit the knowledge of an effective DL model from other contexts to resolve another task in cybersecurity. Our DL-based IDSs are built and trained with the NSL-KDD and CICIDS2018 dataset in both fine-tuning and feature extractor strategy of transfer learning. Then, it is integrated with the SDN controller to analyze traffic flows retrieved from OpenFlow statistics to recognize the anomaly action in the network.
4
Kuchinsky, Stefanie E., and Henk J. Haarmann. "Neuroscience Perspectives on Cognitive Training." In Cognitive and Working Memory Training, 79–104. Oxford University Press, 2019. http://dx.doi.org/10.1093/oso/9780199974467.003.0005.
Full textAbstract:
The aim of this chapter is to spark a discussion regarding how cognitive neuroscience research can aid in the evaluation and development of effective cognitive training protocols. In particular, the authors pose questions relating to whether training-related neural plasticity (i.e., changes in brain function and structure in response to experience) could be used to facilitate the identification and targeting of the neural systems (for working memory and other executive functions) that both support performance on a desired outcome task (e.g., speech recognition) and are alterable via training. The chapter describes approaches that provide unique methodological perspectives for understanding the neural systems that support training-related improvements in cognition. The chapter also highlights the multiple challenges that have emerged from behavioral studies of cognitive training and that neuroscience techniques may help to address, including: establishing the extent to which cognitive training benefits exist for trained tasks and materials, transfer to untrained tasks and materials, persist for extended periods of time, and are effective across a range of individuals. Cognitive neuroscience research has begun not only to tackle these challenges but also to pose new questions, such as: Can training benefits be maximized via regulating or stimulating the neural systems that support behavior? How might our current approaches to cognitive training be significantly altered by novel and developing cognitive neuroscience methodologies?
5
Sas, Corina. "Sense of Presence." In Encyclopedia of Human Computer Interaction, 511–17. IGI Global, 2006. http://dx.doi.org/10.4018/978-1-59140-562-7.ch076.
Full textAbstract:
Sense of presence is one of the most interesting phenomena that enriches users’ experiences of interacting with any type of system. It allows users to be there (Schloerb & Sheridan, 1995) and to perceive the virtual world as another world in which they really exist. The interest in presence phenomenon is not novel (Gerrig, 1993), but it has grown lately due to the advent of virtual reality (VR) technology. The specific characteristics of virtual environments (VEs) transform them into suitable experimental testbeds for studies in various research areas. This also resuscitated the interest in presence, and much work has focused on the development of a theoretical body of knowledge and on a whole set of experimental studies aimed at understanding, explaining, measuring, or predicting presence. All of these efforts have been made to increase the understanding of how presence can be manipulated within the VEs, particularly within the application areas where presence potential has been acknowledged. Probably one of the most important reasons motivating presence research is the relationship it holds with task performance. This debatable relationship together with the more obvious one between presence and user satisfaction suggest that presence may play an important role in the perceived system usability. Since presence may act as a catalyst for the learning potential of VEs, it can be harnessed for the training and transfer of skills (Mantovani & Castelnuovo, 1998; Schank, 1997). The potential of presence to increase the pervasive power of the delivered content motivates research on presence impact on e-marketing and advertising (Grigorovici, 2003). Another promising application area for presence research is within the realm of cognitive therapy of phobias (Strickland et al., 1997). The highly subjective nature of presence continues to challenge researchers to find appropriate methodologies and instruments for measuring it. This is reflected in the ongoing theoretical work of conceptualizing a sense of presence. The difficulties related to investigating presence led to a large set of definitions and measuring tools. The purpose of this article is to introduce the concept of presence. The first section offers some conceptual delimitations related to presence construct. The second section describes its main determinants along two dimensions (i.e., technological factors and human factors). The third section addresses the challenges of measuring presence, offering also an overview of the main methods, tools, and instruments developed for assessing it. The fourth section presents the complex relationship between presence and task performance.
6
Daisy, Anjali. "Knowledge Graph Generation." In Advances in Computer and Electrical Engineering, 115–21. IGI Global, 2020. http://dx.doi.org/10.4018/978-1-7998-1159-6.ch007.
Full textAbstract:
Nowadays, as computer systems are expected to be intelligent, techniques that help modern applications to understand human languages are in much demand. Amongst all the techniques, the latent semantic models are the most important. They exploit the latent semantics of lexicons and concepts of human languages and transform them into tractable and machine-understandable numerical representations. Without that, languages are nothing but combinations of meaningless symbols for the machine. To provide such learning representation, embedding models for knowledge graphs have attracted much attention in recent years since they intuitively transform important concepts and entities in human languages into vector representations, and realize relational inferences among them via simple vector calculation. Such novel techniques have effectively resolved a few tasks like knowledge graph completion and link prediction, and show the great potential to be incorporated into more natural language processing (NLP) applications.
7
Häkkilä, Jonna, and Jenine Beekhuyzen. "Using Mobile Communication Technology in Student Mentoring." In Encyclopedia of Human Computer Interaction, 680–85. IGI Global, 2006. http://dx.doi.org/10.4018/978-1-59140-562-7.ch102.
Full textAbstract:
Information technology (IT), computer science, and other related disciplines have become significant both in society and within the field of education. Resulting from the last decades’ considerable developments towards a global information society, the demand for a qualified IT workforce has increased. The integration of information technology into the different sectors of every day life is increasing the need for large numbers of IT professionals. Additionally, the need for nearly all workers to have general computing skills suggests possibilities for an individual to face inequality or suffer from displacement in modern society if they lack these skills, further contributing to the digital divide. Thus, the importance of IT education has a greater importance than ever for the whole of society. Despite the advances and mass adoption of new technologies, IT and computing education continually suffers from low participant numbers, and high dropout and transfer rates. This problem has been somewhat addressed by introducing mentoring programs (von Hellens, Nielsen, Doyle, & Greenhill, 1999) where a student is given a support person, a mentor, who has a similar education background but has graduated and is employed in industry. Although the majority of these programs have been considered successful, it is important to note that it is difficult to easily measure success in this context. In this article, we introduce a novel approach to mentoring which was adopted as part of an ongoing, traditional-type mentoring program in a large Australian university. The approach involved introducing modern communications technology, specifically mobile phones having an integrated camera and the capability to make use of multimedia messaging services (MMS). As mobile phones have become an integrated part of our everyday life (with high adoption rates) and are an especially common media of communication among young people, it was expected that the use of the phones could be easily employed to the mentoring program (phones were provided for the participants). Short message service (SMS), for example text messaging, has become a frequently used communication channel (Grinter & Eldridge 2003). In addition to text, photo sharing has also quickly taken off with MMS capable mobile phones becoming more widespread. The ability to exchange photos increases the feeling of presence (Counts & Fellheimer, 2004), and the possibility to send multimedia messages with mobile phones has created a new form of interactive storytelling (Kurvinen, 2003). Cole and Stanton (2003) found the pictorial information exchange as a potential tool for children’s collaboration during their activities in story telling, adventure gaming and for field trip tasks. Encouraged by these experiences, we introduced mobile mentoring as part of a traditional mentoring program, and present the experiences. It is hoped that these experiences can affirm the legitimacy of phone mentoring as a credible approach to mentoring. The positive and negative experiences presented in this article can help to shape the development of future phone mentoring programs.
8
Häkkilä, Jonna, and Jenine Beekhuyzen. "Using Mobile Communication Technology in Student Mentoring." In Mobile Computing, 1351–58. IGI Global, 2009. http://dx.doi.org/10.4018/978-1-60566-054-7.ch111.
Full textAbstract:
Information technology (IT), computer science, and other related disciplines have become signifi- cant both in society and within the field of education. Resulting from the last decades’ considerable developments towards a global information society, the demand for a qualified IT workforce has increased. The integration of information technology into the different sectors of every day life is increasing the need for large numbers of IT professionals. Additionally, the need for nearly all workers to have general computing skills suggests possibilities for an individual to face inequality or suffer from displacement in modern society if they lack these skills, further contributing to the digital divide. Thus, the importance of IT education has a greater importance than ever for the whole of society. Despite the advances and mass adoption of new technologies, IT and computing education continually suffers from low participant numbers, and high dropout and transfer rates. This problem has been somewhat addressed by introducing mentoring programs (von Hellens, Nielsen, Doyle, & Greenhill, 1999) where a student is given a support person, a mentor, who has a similar education background but has graduated and is employed in industry. Although the majority of these programs have been considered successful, it is important to note that it is difficult to easily measure success in this context. In this article, we introduce a novel approach to mentoring which was adopted as part of an ongoing, traditional-type mentoring program in a large Australian university. The approach involved introducing modern communications technology, specifically mobile phones having an integrated camera and the capability to make use of multimedia messaging services (MMS). As mobile phones have become an integrated part of our everyday life (with high adoption rates) and are an especially common media of communication among young people, it was expected that the use of the phones could be easily employed to the mentoring program (phones were provided for the participants). Short message service (SMS), for example text messaging, has become a frequently used communication channel (Grinter & Eldridge 2003). In addition to text, photo sharing has also quickly taken off with MMS capable mobile phones becoming more widespread. The ability to exchange photos increases the feeling of presence (Counts & Fellheimer, 2004), and the possibility to send multimedia messages with mobile phones has created a new form of interactive storytelling (Kurvinen, 2003). Cole and Stanton (2003) found the pictorial information exchange as a potential tool for children’s collaboration during their activities in story telling, adventure gaming and for field trip tasks. Encouraged by these experiences, we introduced mobile mentoring as part of a traditional mentoring program, and present the experiences. It is hoped that these experiences can affirm the legitimacy of phone mentoring as a credible approach to mentoring. The positive and negative experiences presented in this article can help to shape the development of future phone mentoring programs.
Conference papers on the topic "Novel task transfer"
1
Um, Terry Taewoong, Myoung Soo Park, and Jung-Min Park. "Independent Joint Learning: A novel task-to-task transfer learning scheme for robot models." In 2014 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2014. http://dx.doi.org/10.1109/icra.2014.6907694.
Full text
2
Soh, Harold, Shu Pan, Min Chen, and David Hsu. "Trust Dynamics and Transfer across Human-Robot Interaction Tasks: Bayesian and Neural Computational Models." In Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}. California: International Joint Conferences on Artificial Intelligence Organization, 2019. http://dx.doi.org/10.24963/ijcai.2019/868.
Full textAbstract:
This work contributes both experimental findings and novel computational human-robot trust models for multi-task settings. We describe Bayesian non-parametric and neural models, and compare their performance on data collected from real-world human-subjects study. Our study spans two distinct task domains: household tasks performed by a Fetch robot, and a virtual reality driving simulation of an autonomous vehicle performing a variety of maneuvers. We find that human trust changes and transfers across tasks in a structured manner based on perceived task characteristics. Our results suggest that task-dependent functional trust models capture human trust in robot capabilities more accurately, and trust transfer across tasks can be inferred to a good degree. We believe these models are key for enabling trust-based robot decision-making for natural human-robot interaction.
3
Zheng, Zimu, Yuqi Wang, Quanyu Dai, Huadi Zheng, and Dan Wang. "Metadata-driven Task Relation Discovery for Multi-task Learning." In Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}. California: International Joint Conferences on Artificial Intelligence Organization, 2019. http://dx.doi.org/10.24963/ijcai.2019/615.
Full textAbstract:
Task Relation Discovery (TRD), i.e., reveal the relation of tasks, has notable value: it is the key concept underlying Multi-task Learning (MTL) and provides a principled way for identifying redundancies across tasks. However, task relation is usually specifically determined by data scientist resulting in the additional human effort for TRD, while transfer based on brute-force methods or mere training samples may cause negative effects which degrade the learning performance. To avoid negative transfer in an automatic manner, our idea is to leverage commonly available context attributes in nowadays systems, i.e., the metadata. In this paper, we, for the first time, introduce metadata into TRD for MTL and propose a novel Metadata Clustering method, which jointly uses historical samples and additional metadata to automatically exploit the true relatedness. It also avoids the negative transfer by identifying reusable samples between related tasks. Experimental results on five real-world datasets demonstrate that the proposed method is effective for MTL with TRD, and particularly useful in complicated systems with diverse metadata but insufficient data samples. In general, this study helps in automatic relation discovery among partially related tasks and sheds new light on the development of TRD in MTL through the use of metadata as apriori information.
4
Zhu, Mingrui, Nannan Wang, Xinbo Gao, Jie Li, and Zhifeng Li. "Face Photo-Sketch Synthesis via Knowledge Transfer." In Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}. California: International Joint Conferences on Artificial Intelligence Organization, 2019. http://dx.doi.org/10.24963/ijcai.2019/147.
Full textAbstract:
Despite deep neural networks have demonstrated strong power in face photo-sketch synthesis task, their performance, however, are still limited by the lack of training data (photo-sketch pairs). Knowledge Transfer (KT), which aims at training a smaller and fast student network with the information learned from a larger and accurate teacher network, has attracted much attention recently due to its superior performance in the acceleration and compression of deep neural networks. This work has brought us great inspiration that we can train a relatively small student network on very few training data by transferring knowledge from a larger teacher model trained on enough training data for other tasks. Therefore, we propose a novel knowledge transfer framework to synthesize face photos from face sketches or synthesize face sketches from face photos. Particularly, we utilize two teacher networks trained on large amount of data in related task to learn the knowledge of face photos and face sketches separately and transfer them to two student networks simultaneously. In addition, the two student networks, one for photo ? sketch task and the other for sketch ? photo task, can transfer their knowledge mutually. With the proposed method, we can train our model which has superior performance using a small set of photo-sketch pairs. We validate the effectiveness of our method across several datasets. Quantitative and qualitative evaluations illustrate that our model outperforms other state-of-the-art methods in generating face sketches (or photos) with high visual quality and recognition ability.
5
Fang, Yuchun, Zhengyan Ma, Zhaoxiang Zhang, Xu-Yao Zhang, and Xiang Bai. "Dynamic Multi-Task Learning with Convolutional Neural Network." In Twenty-Sixth International Joint Conference on Artificial Intelligence. California: International Joint Conferences on Artificial Intelligence Organization, 2017. http://dx.doi.org/10.24963/ijcai.2017/231.
Full textAbstract:
Multi-task learning and deep convolutional neural network (CNN) have been successfully used in various fields. This paper considers the integration of CNN and multi-task learning in a novel way to further improve the performance of multiple related tasks. Existing multi-task CNN models usually empirically combine different tasks into a group which is then trained jointly with a strong assumption of model commonality. Furthermore, traditional approaches usually only consider small number of tasks with rigid structure, which is not suitable for large-scale applications. In light of this, we propose a dynamic multi-task CNN model to handle these problems. The proposed model directly learns the task relations from data instead of subjective task grouping. Due to its flexible structure, it supports task-wise incremental training, which is useful for efficient training of massive tasks. Specifically, we add a new task transfer connection (TTC) between the layers of each task. The learned TTC is able to reflect the correlation among different tasks guiding the model dynamically adjusting the multiplexing of the information among different tasks. With the help of TTC, multiple related tasks can further boost the whole performance for each other. Experiments demonstrate that the proposed dynamic multi-task CNN model outperforms traditional approaches.
6
Tian, Qiangxing, Guanchu Wang, Jinxin Liu, Donglin Wang, and Yachen Kang. "Independent Skill Transfer for Deep Reinforcement Learning." In Twenty-Ninth International Joint Conference on Artificial Intelligence and Seventeenth Pacific Rim International Conference on Artificial Intelligence {IJCAI-PRICAI-20}. California: International Joint Conferences on Artificial Intelligence Organization, 2020. http://dx.doi.org/10.24963/ijcai.2020/401.
Full textAbstract:
Recently, diverse primitive skills have been learned by adopting the entropy as intrinsic reward, which further shows that new practical skills can be produced by combining a variety of primitive skills. This is essentially skill transfer, very useful for learning high-level skills but quite challenging due to the low efficiency of transferring primitive skills. In this paper, we propose a novel efficient skill transfer method, where we learn independent skills and only independent components of skills are transferred instead of the whole set of skills. More concretely, independent components of skills are obtained through independent component analysis (ICA), which always have a smaller amount (or lower dimension) compared with their mixtures. With a lower dimension, independent skill transfer (IST) exhibits a higher efficiency on learning a given task. Extensive experiments including three robotic tasks demonstrate the effectiveness and high efficiency of our proposed IST method in comparison to direct primitive-skill transfer and conventional reinforcement learning.
7
Lee, Seungwon, James Stokes, and Eric Eaton. "Learning Shared Knowledge for Deep Lifelong Learning using Deconvolutional Networks." In Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}. California: International Joint Conferences on Artificial Intelligence Organization, 2019. http://dx.doi.org/10.24963/ijcai.2019/393.
Full textAbstract:
Current mechanisms for knowledge transfer in deep networks tend to either share the lower layers between tasks, or build upon representations trained on other tasks. However, existing work in non-deep multi-task and lifelong learning has shown success with using factorized representations of the model parameter space for transfer, permitting more flexible construction of task models. Inspired by this idea, we introduce a novel architecture for sharing latent factorized representations in convolutional neural networks (CNNs). The proposed approach, called a deconvolutional factorized CNN, uses a combination of deconvolutional factorization and tensor contraction to perform flexible transfer between tasks. Experiments on two computer vision data sets show that the DF-CNN achieves superior performance in challenging lifelong learning settings, resists catastrophic forgetting, and exhibits reverse transfer to improve previously learned tasks from subsequent experience without retraining.
8
Wu, Qianhui, Zijia Lin, Börje F. Karlsson, Biqing Huang, and Jian-Guang Lou. "UniTrans : Unifying Model Transfer and Data Transfer for Cross-Lingual Named Entity Recognition with Unlabeled Data." In Twenty-Ninth International Joint Conference on Artificial Intelligence and Seventeenth Pacific Rim International Conference on Artificial Intelligence {IJCAI-PRICAI-20}. California: International Joint Conferences on Artificial Intelligence Organization, 2020. http://dx.doi.org/10.24963/ijcai.2020/543.
Full textAbstract:
Prior work in cross-lingual named entity recognition (NER) with no/little labeled data falls into two primary categories: model transfer- and data transfer-based methods. In this paper, we find that both method types can complement each other, in the sense that, the former can exploit context information via language-independent features but sees no task-specific information in the target language; while the latter generally generates pseudo target-language training data via translation but its exploitation of context information is weakened by inaccurate translations. Moreover, prior work rarely leverages unlabeled data in the target language, which can be effortlessly collected and potentially contains valuable information for improved results. To handle both problems, we propose a novel approach termed UniTrans to Unify both model and data Transfer for cross-lingual NER, and furthermore, leverage the available information from unlabeled target-language data via enhanced knowledge distillation. We evaluate our proposed UniTrans over 4 target languages on benchmark datasets. Our experimental results show that it substantially outperforms the existing state-of-the-art methods.
9
Guo, Yuchen, Guiguang Ding, Jungong Han, and Yue Gao. "SitNet: Discrete Similarity Transfer Network for Zero-shot Hashing." In Twenty-Sixth International Joint Conference on Artificial Intelligence. California: International Joint Conferences on Artificial Intelligence Organization, 2017. http://dx.doi.org/10.24963/ijcai.2017/245.
Full textAbstract:
Hashing has been widely utilized for fast image retrieval recently. With semantic information as supervision, hashing approaches perform much better, especially when combined with deep convolution neural network(CNN). However, in practice, new concepts emerge every day, making collecting supervised information for re-training hashing model infeasible. In this paper, we propose a novel zero-shot hashing approach, called Discrete Similarity Transfer Network (SitNet), to preserve the semantic similarity between images from both ``seen'' concepts and new ``unseen'' concepts. Motivated by zero-shot learning, the semantic vectors of concepts are adopted to capture the similarity structures among classes, making the model trained with seen concepts generalize well for unseen ones benefiting from the transferability of the semantic vector space. We adopt a multi-task architecture to exploit the supervised information for seen concepts and the semantic vectors simultaneously. Moreover, a discrete hashing layer is integrated into the network for hashcode generating to avoid the information loss caused by real-value relaxation in training phase, which is a critical problem in existing works. Experiments on three benchmarks validate the superiority of SitNet to the state-of-the-arts.
10
Liu, Ziyu, Wei Shao, Jie Zhang, Min Zhang, and Kun Huang. "Transfer Learning via Optimal Transportation for Integrative Cancer Patient Stratification." In Thirtieth International Joint Conference on Artificial Intelligence {IJCAI-21}. California: International Joint Conferences on Artificial Intelligence Organization, 2021. http://dx.doi.org/10.24963/ijcai.2021/380.
Full textAbstract:
The Stratification of early-stage cancer patients for the prediction of clinical outcome is a challenging task since cancer is associated with various molecular aberrations. A single biomarker often cannot provide sufficient information to stratify early-stage patients effectively. Understanding the complex mechanism behind cancer development calls for exploiting biomarkers from multiple modalities of data such as histopathology images and genomic data. The integrative analysis of these biomarkers sheds light on cancer diagnosis, subtyping, and prognosis. Another difficulty is that labels for early-stage cancer patients are scarce and not reliable enough for predicting survival times. Given the fact that different cancer types share some commonalities, we explore if the knowledge learned from one cancer type can be utilized to improve prognosis accuracy for another cancer type. We propose a novel unsupervised multi-view transfer learning algorithm to simultaneously analyze multiple biomarkers in different cancer types. We integrate multiple views using non-negative matrix factorization and formulate the transfer learning model based on the Optimal Transport theory to align features of different cancer types. We evaluate the stratification performance on three early-stage cancers from the Cancer Genome Atlas (TCGA) project. Comparing with other benchmark methods, our framework achieves superior accuracy for patient outcome prediction.
Reports on the topic "Novel task transfer"
1
Jozewicz, Wojciech, and G. T. Rochelle. Theoretical approach for enhanced mass transfer effects in duct flue gas desulfurization processes. Topical report for Task 4, Novel techniques. Office of Scientific and Technical Information (OSTI), September 1991. http://dx.doi.org/10.2172/10125937.
Full text