To see the other types of publications on this topic, follow the link: Perception and learning.
Dissertations / Theses on the topic 'Perception and 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 'Perception and 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
Liu, Chong. "Reinforcement learning with time perception." Thesis, University of Manchester, 2012. https://www.research.manchester.ac.uk/portal/en/theses/reinforcement-learning-with-time-perception(a03580bd-2dd6-4172-a061-90e8ac3022b8).html.
Full textAbstract:
Classical value estimation reinforcement learning algorithms do not perform very well in dynamic environments. On the other hand, the reinforcement learning of animals is quite flexible: they can adapt to dynamic environments very quickly and deal with noisy inputs very effectively. One feature that may contribute to animals' good performance in dynamic environments is that they learn and perceive the time to reward. In this research, we attempt to learn and perceive the time to reward and explore situations where the learned time information can be used to improve the performance of the learning agent in dynamic environments. The type of dynamic environments that we are interested in is that type of switching environment which stays the same for a long time, then changes abruptly, and then holds for a long time before another change. The type of dynamics that we mainly focus on is the time to reward, though we also extend the ideas to learning and perceiving other criteria of optimality, e.g. the discounted return, so that they can still work even when the amount of reward may also change. Specifically, both the mean and variance of the time to reward are learned and then used to detect changes in the environment and to decide whether the agent should give up a suboptimal action. When a change in the environment is detected, the learning agent responds specifically to the change in order to recover quickly from it. When it is found that the current action is still worse than the optimal one, the agent gives up this time's exploration of the action and then remakes its decision in order to avoid longer than necessary exploration. The results of our experiments using two real-world problems show that they have effectively sped up learning, reduced the time taken to recover from environmental changes, and improved the performance of the agent after the learning converges in most of the test cases compared with classical value estimation reinforcement learning algorithms. In addition, we have successfully used spiking neurons to implement various phenomena of classical conditioning, the simplest form of animal reinforcement learning in dynamic environments, and also pointed out a possible implementation of instrumental conditioning and general reinforcement learning using similar models.
2
Malyan, R. R. "Machine learning for handprinted character perception." Thesis, Kingston University, 1989. http://eprints.kingston.ac.uk/20527/.
Full textAbstract:
Humans are well suited to the reading of textual information, but unfortunately it has not yet been possible to develop a machine to emulate this form of human behaviour. In the past, machines have been characterised by having static forms of specific knowledge necessary for character recognition. The resulting form of reading behaviour is most uncharacteristic of the way humans perceive textual information. The major problem with handprinted character recognition is the infinite variability in the character shapes and the ambiguities many of these shapes exhibit. Human perception of handprinted characters makes extensive use of "world knowledge" to remove such ambiguities. Humans are also continually modifying their world knowledge to further enhance their reading behaviour by acquiring new knowledge as they read. An information processing model for perception and learning of handprinted characters is proposed. The function of the model is to enable ambiguous character descriptions to converge to single character classifications. The accuracy of this convergence improves with reading experience on handprinted text. The model consists of three compon,ent parts. Firstly, a character classifier to recognise character patterns. These patterns may be both distorted anq noisy, where distortion is defined to be a consistent variability from known archetypical character descriptions and noise as a random inconsistent variability in character shape. Secondly, a perceptive mechanism that makes inferences from an incomplete linguistic world model of an author or of a specific domain of discourse from many authors. Finally, a incremental learning capability is integrated into the character classifier and perceptive mechanisms. This is to enable the internal world model to be continually adaptive to either changes in the domain of discourse or to different authors. A demonstrator is described, together with a summary of experimental results that clearly show the improvement in machine perception which results from continuous incremental learning.
3
Öhlander, Andersson Lina. "English Language Learning : Student's Perception on Their Own Language Learning." Thesis, Högskolan i Gävle, Avdelningen för humaniora, 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:hig:diva-14371.
Full textAbstract:
This is a qualitative study, which aims at looking closer into how eight students look upon their own English perceiving skills. A qualitative interview method was used to interview eight students in upper secondary school. The participants were four girls and four boys. The result from the interviews have been presented under three different headings, which are as follows: Motivation, Classroom and Acquisition. A lot of studies have been done on the subject of language learning and it has resulted in many theories, and the ones that seemed relevant for this study have been brought up and connected to the answers the students gave. Most of the students felt motivated to learn English and the main reason was their future job plans. In the classroom, the participants thought that the teacher's behaviour and attitude towards the English subject was the most important factor to motivate them. The interview results showed that the student's thought that the best way to learn English was through media, foremost by speaking and writing with their friends on the computer. Those answers can be connected to something that the Russian psychologist Lev S. Vygotskij presents with the socio-cultural theory, were he promotes the idea that the best way to learn a new language is to interact with other people.
4
Karanka, Joni. "Learning in binocular time-to-contact perception." Thesis, Cardiff University, 2008. http://orca.cf.ac.uk/54808/.
Full textAbstract:
Time-to-contact (TTC) is defined as the remaining time for an object to reach the observer. This is an important quantity for timing an action such as hitting or catching a ball. This thesis deals with learning processes in TTC perception when binocular vision is available. Chapter 1 studies the learning of TTC in relative discrimination tasks. We did not find learning in this task, but we found that simple correlates of TTC explained the judgments made by the participants. Chapter 2 studies the learning of TTC in absolute estimation tasks. We found that the variable and constant error of the responses reduced with training. Chapter 3 studied the use of feedback in calibrating the timing of TTC estimates. We found that biased timing produced changes in the constant error, suggesting that TTC calibration is guided by feedback. Chapter 4 studied if the reduction of variable error was due to an increased perceptual sensitivity to TTC. However, we failed to find transfer from the absolute estimation tasks to relative discrimination tasks, suggesting that the learning found in Chapter 2 might not be of perceptual origin. In Chapter 5 we studied a large group of participants in laboratory tasks and a natural hitting task. We found that the performance in relative discrimination and absolute estimation tasks could be used to predict hitting skill. This suggests that the perception of TTC can be linked with interceptive timing. Taken together, these results suggest that perceptual sensitivity to TTC changes slightly -if at all- with training, but changes in perceptuo-motor mapping and calibration of the estimates that increase interceptive performance do take place.
5
Wozny, David R. "Statistical inference in multisensory perception and learning." Diss., Restricted to subscribing institutions, 2009. http://proquest.umi.com/pqdweb?did=1970597951&sid=1&Fmt=2&clientId=1564&RQT=309&VName=PQD.
Full text
6
Kulkarni, Tejas Dattatraya. "Learning structured representations for perception and control." Thesis, Massachusetts Institute of Technology, 2016. http://hdl.handle.net/1721.1/107557.
Full textAbstract:
Thesis: Ph. D., Massachusetts Institute of Technology, Department of Brain and Cognitive Sciences, 2016.Cataloged from PDF version of thesis.
Includes bibliographical references (pages 117-129).
I argue that the intersection of deep learning, hierarchical reinforcement learning, and generative models provides a promising avenue towards building agents that learn to produce goal-directed behavior given sensations. I present models and algorithms that learn from raw observations and will emphasize on minimizing their sample complexity and number of training steps required for convergence. To this end, I introduce hierarchical variants of deep reinforcement learning algorithms, which produce and utilize temporally extended abstractions over actions. I also present a hybrid model-free and model-based deep reinforcement learning model, which can also be potentially used to automatically extract subgoals for bootstrapping temporal abstractions. I will then present a model-based approach for perception, which unifies deep learning and probabilistic models, to learn powerful representations of images without labeled data or external rewards. Learning goal-directed behavior with sparse and delayed rewards is a fundamental challenge for reinforcement learning algorithms. The primary difficulty arises due to insufficient exploration, resulting in an agent being unable to learn robust value functions. I present the Deep Hierarchical Reinforcement Learning (h-DQN) approach, which integrates hierarchical value functions operating at different time scales, along with goal-driven intrinsically motivated behavior for efficient exploration. Intrinsically motivated agents can explore new behavior for its own sake rather than to directly solve problems. Such intrinsic behaviors could eventually help the agent solve tasks posed by the environment. h-DQN allows for flexible goal specifications, such as functions over entities and relations. This provides an efficient space for exploration in complicated environments. I will demonstrate h-DQN's ability to learn optimal behavior given raw pixels in environments with very sparse and delayed feedback. I will then introduce the Deep Successor Reinforcement (DSR) learning approach. DSR is a hybrid model-free and model-based RL algorithm. It learns the value function of a state by taking the inner product between the state's expected future feature occupancy and the corresponding immediate rewards. This factorization of the value function has several appealing properties - increased sensitivity to changes in the reward structure and potentially the ability to automatically extract subgoals for learning temporal abstractions. Finally, I argue for the need for better representations of images, both in reinforcement learning tasks and in general. Existing deep learning approaches learn useful representations given lots of labeled data or rewards. Moreover, they also lack the inductive biases needed to disentangle causal structure in images such as objects, shape, pose and other intrinsic scene properties. I present generative models of vision, often referred to as analysis-by-synthesis approaches, by combining deep generative methods with probabilistic modeling. This approach aims to learn structured representations of images given raw observations. I argue that such intermediate representations will be crucial to scale-up deep reinforcement learning algorithms, and to bridge the gap between machine and human learning.
by Tejas Dattatraya Kulkarni.
Ph. D.
7
Ayeme, Bukola. "Teachers` Perception of Outdoor Learning : Benefits and Challenges of Outdoor Learning." Thesis, Linköpings universitet, Institutionen för beteendevetenskap och lärande, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-166745.
Full textAbstract:
Outdoor learning has become very visible in recent times ,it is seen in different public medias such as magazines, on television, on various websites on internet, in the press and on public notice boards in different countries, accompanying different advertisements displaying a healthy lifestyle especially in early years of studies ( preschool ).The author seeks to address the perception of Erasmus project “Dehors ” teachers` experience outdoor, focusing majorly on the benefits and difficulties that these preschool teachers face while teaching outdoors. Furthermore, teachers are known to be role-models for their students and their opinion about their jobs matters a lot in displaying their duties as educators. Preschool children aged 0-6 years spend more time in school more than home, at least a minimum of five days in a week so ultimately attitudes of teachers largely have a positive or negative effect on school children. The aim of the present dissertation project is to explore how the teachers perceive outdoor learning based on their experiences outdoors. This study explored the components that characterize teachers` perception of outdoor learning. This research includes two set of interviews which were used to investigate both teachers` outdoor activities performed in Latvia and Swedish preschools. Outdoor learning has made a distinctive difference between the traditional learning approach of “stand and deliver” model which has systematically been changed to “guide on the side” model which educationalist view as a good method of impacting knowledge to learners, instead of giving knowledge as it was practiced before but in recent times, outdoor leaning processes helps to create an atmosphere for co-learning and not an isolated endeavours which is gradually been replaced by outdoor learning approach of “tell me and I will forget with “show me and I will remember”. These results provided a great insight on teachers` experiences of outdoor learning in the nature and on asphalt. It can be concluded that outdoor learning approach can be adaptable in the Latvian and Swedish contexts in promoting the development of preschool teachers therefore, there is a need for further research to promote effectiveness of outdoor teaching in Latvia and Swedish preschools.
8
Kacelnik, Oliver. "Perceptual learning in sound localization." Thesis, University of Oxford, 2002. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.270638.
Full text
9
McGuire, Grant Leese. "Phonetic category learning." Columbus, Ohio : Ohio State University, 2007. http://rave.ohiolink.edu/etdc/view?acc%5Fnum=osu1190065715.
Full text
10
Pilling-Cormick, Jane. "Development of the Self-Directed Learning Perception Scale." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1996. http://www.collectionscanada.ca/obj/s4/f2/dsk3/ftp04/NQ41543.pdf.
Full text
11
Parker-Stephen, Evan Stimson James A. "Learning about change information, motivation, and political perception /." Chapel Hill, N.C. : University of North Carolina at Chapel Hill, 2007. http://dc.lib.unc.edu/u?/etd,763.
Full textAbstract:
Thesis (Ph. D.)--University of North Carolina at Chapel Hill, 2007.Title from electronic title page (viewed Dec. 18, 2007). "... in partial fulfillment of the requirements for the degree of Doctor of Philosophy in the Department of Political Science." Discipline: Political Science; Department/School: Political Science.
12
Eagle, Nathan Norfleet. "Machine perception and learning of complex social systems." Thesis, Massachusetts Institute of Technology, 2005. http://hdl.handle.net/1721.1/32498.
Full textAbstract:
Thesis (Ph. D.)--Massachusetts Institute of Technology, School of Architecture and Planning, Program in Media Arts and Sciences, 2005.Includes bibliographical references (p. 125-136).
The study of complex social systems has traditionally been an arduous process, involving extensive surveys, interviews, ethnographic studies, or analysis of online behavior. Today, however, it is possible to use the unprecedented amount of information generated by pervasive mobile phones to provide insights into the dynamics of both individual and group behavior. Information such as continuous proximity, location, communication and activity data, has been gathered from the phones of 100 human subjects at MIT. Systematic measurements from these 100 people over the course of eight months has generated one of the largest datasets of continuous human behavior ever collected, representing over 300,000 hours of daily activity. In this thesis we describe how this data can be used to uncover regular rules and structure in behavior of both individuals and organizations, infer relationships between subjects, verify self- report survey data, and study social network dynamics. By combining theoretical models with rich and systematic measurements, we show it is possible to gain insight into the underlying behavior of complex social systems.
by Nathan Norfleet Eagle.
Ph.D.
13
Notman, Leslie. "On perceptual learning, categorical perception and perceptual expertise." Thesis, University of Surrey, 2005. http://epubs.surrey.ac.uk/844066/.
Full textAbstract:
The empirical work reported in the current thesis set out to explore the relationship between perceptual expertise, categorical perception (CP) and perceptual learning. Evidence to support the idea that the way people organise the world into categories can qualitatively affect their perception of it has been provided by CP research. Recent work indicates that categorisation experience can lead to enhanced sensitivity to diagnostic stimulus features and is consistent with the possibility that, as experts have learned to distinguish among objects, they have also acquired new ways of perceptually structuring the objects to be categorised. Nevertheless, there is debate about whether these effects are really perceptual and if so about the mechanisms and locus of learning. Here, experiments were designed to test whether the process of acquiring perceptual categories drives a perceptual learning process that enhances the discrimination of category relevant features thereby contributing to the development of perceptual expertise. The work therefore sought to test the possibility that category learning could drive changes to early stages of perceptual processing. Two classes of stimuli were used to address these issues. Initial experiments showed that learning to categorise Gabor patches can lead to learned CP effects that are specific to the trained spatial frequency, orientation and retinal location. Experiments using morphed cervical cell stimuli showed that expert cervical screeners have acquired heightened discrimination to cells that cross the normal/abnormal category boundary and that training novices to categorise cells as normal or abnormal can also lead to retinotopically specific learned CP effects. Taken together, the results reported in the current thesis support a general explanation of CP effects arising from categorisation driven perceptual learning at early stages of visual processing. Furthermore, the work speculated that modifications to intra-cortical connections at this stage of processing may underpin the learned CP effects observed.
14
Ozawa, Michiyo. "Japanese Students' Perception of Their Language Learning Strategies." PDXScholar, 1996. https://pdxscholar.library.pdx.edu/open_access_etds/5160.
Full textAbstract:
Students' use of language learning strategies (LLSs) is affected by their educational backgrounds and academic requirements, and so are their attitudes toward language learning. This study investigates Japanese students' perception of their English LLSs in different language environments: Japan and the United States. A group of 43 Japanese students from Otemae College participated in a cultural study program at Portland State University. The group consisted of 28 students who studied for two terms (ST Group) and 15 students who studied for three terms (LT Group). In this study, a combination of a self-assessment questionnaire, dialogue journals, and a card-ranking activity was employed. The self-assessment questionnaire, SILL (Rebecca Oxford's Strategy Inventory for Language Learning), was administered at different times during the learning period for identification of students' English LLSs in Japan (Ll) and in the United States (L2). The SILL provided this study with quantitative data; whereas, dialogue journals and the card ranking activity supplied qualitative data that more insightfully indicated students' perception of language learning, learning experiences, and insight into the students themselves. Dialogue journals allowed students to record their positive and negative experiences in the L2 related to language learning, emotions, concerns, problems, and questions. The students' LLSs increased in frequency and variety of use when the language environment changed from the Ll to the L2. The LLSs of the LT Group continued to improve during an additional term in the L2. Conversely, the LLS use by the ST Group regressed after only four months back in the Ll (except Affective and Social Strategies). The results of the SILL indicated direct strategies were adjusted according to English learning experience in a different learning environment. Three administrations of the SILL, dialogue journals, and the card ranking activity gave students opportunities to review the process of their English learning. This process functioned in raising students' awareness of language learning from cognitive, psychological, social, and cultural perspectives. Such conceptual development of metalinguistic awareness of the language and culture helped the students recognize their language learning experiences in the L2 as the process of human development.
15
Skarenstedt, Jeff. "Students´ perception about flipped classroom in learning mathematics." Thesis, Malmö universitet, Fakulteten för lärande och samhälle (LS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:mau:diva-29564.
Full text
16
Ngo, Quang Thanh. "Online perception with machine learning for automated driving." Technische Universität Chemnitz, 2019. https://monarch.qucosa.de/id/qucosa%3A73111.
Full textAbstract:
The understanding of the environment is the critical ability not only for the living creature but also for automation fields like the robot, automated car, and intelligent system. Especially for some essential task in the domain of automotive such as autonomous driving, path planning, localization, and object detection, the more information we gather, the better the result we get. Intelligent vehicle technology relies on sensorial perception to understand the surroundings of the vehicle. The objective of the research is developing a cooperative online perception system with semantic segmentation for automated driving and improving the current semantic segmentation framework to make it more robust and more suitable for our future projects.
17
Cote, Courtney. "Children's Perception of the Learning Value of Play." Thesis, Minot State University, 2017. http://pqdtopen.proquest.com/#viewpdf?dispub=10684898.
Full textAbstract:
Play time has been thought to be an important part of the Kindergarten experience. However; over the years there has been a shift in what is seen in the Kindergarten classroom. Rarely is play seen in the classroom; rather there is more focus on seated work for efficiency of meeting all standards during the year. This thesis focused on how important play in the Kindergarten classroom and how much children learn through play that examined the child’s perception of what they learned after a mixture of guided play and free play centers. Through observations of the children and interviews, this thesis showed learning can be seen while in play through the eyes of children. Students’ observations showed learning through both independent play as well as playing in groups of students. Every station observed through this study showed some type of learning whether it was a general understanding of concepts or a very specific understanding of the concepts the students were introduced to during play. This study also showed that students learned in both guided and free play settings.
18
Bolton, Trevor. "Teacher perception of Key Skills and transfer." Thesis, Lancaster University, 2000. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.369597.
Full text
19
Whaley, Christopher J. "Cross-modality learning and redundancy with auditory and visual displays." Diss., Georgia Institute of Technology, 1997. http://hdl.handle.net/1853/30925.
Full text
20
Wibåge, Anna, and Sara Södersten. "Healthcare students perception of their readiness for interprofessional learning." Thesis, Uppsala universitet, Institutionen för folkhälso- och vårdvetenskap, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-351450.
Full textAbstract:
Introduction: Interprofessional Learning (IPL) is an approach that teaches students from different disciplines to share their professional knowledge in order to gain a more complex understanding of the situation at hand. According to WHO, interprofessional learning strengthens communication and the collaborative practice which in turn improves health outcomes for patients. Insufficient interprofessional communication due to inexperience with interprofessional teamwork can affect patients’ safety. Aim: To compare differences in nursing- and medical students readiness for interprofessional learning in Vietnam and if they believe that IPL could affect the quality of communication with patients. Method: A quantitative study was conducted, with a descriptive approach where the population consisted of nursing- and medical students at University of Medicine and Pharmacy in Ho Chi Minh City, Vietnam. The data was collected through a structured questionnaire called Readiness for Interprofessional Learning Scale (RIPLS). Mann Whitney U-test was used for statistical analyzes. Results: A statistical significant difference, between the two professions, was found in four out of nineteen questions. Therefore we could not see a difference in readiness between the two professions. Regarding the students’ perception on IPL and communication, we could not see a statistical difference, the two groups had similar views on the topic. Conclusion: We could only find a few questions that reflected an actual difference (p < 0.05) in opinion between the two professions.
21
Kollmitz, Marina [Verfasser], and Wolfram [Akademischer Betreuer] Burgard. "Perception and learning for mobile robots in populated environments." Freiburg : Universität, 2021. http://d-nb.info/1236500512/34.
Full text
22
Smith, Dennell Lawrence. "Developmental Students' Perception of a First Year Learning Community." ScholarWorks, 2015. https://scholarworks.waldenu.edu/dissertations/1554.
Full textAbstract:
This project study was an evaluation of a first year learning community program for community college students enrolled in developmental coursework at a community college in California. The program had never been evaluated. The evaluation used learning community students' and faculty members' perception as a basis for evaluation, specifically concentrating on areas that promoted student success and areas that needed further refinement. Only former program participants and the program faculty members were eligible for the study. Of the 78 eligible participants, responses from 51 students and the 2 faculty members were collected. The theoretical framework was grounded in Tinto's work with learning communities. Data for the evaluation were collected using surveys with open-ended questions as well as interviews with faculty. The qualitative analysis required theme identification using key words from the surveys and interviews. The results from the study indicated that the learning community provided a social support for student learning that was considered a strength for the program but that various elements of programming such as class scheduling and policies were considered areas needing improvement. The project evaluation resulted in an administrative evaluation report. The findings may be incorporated as recommendations for program improvements and documentation of best practices at the community college. The implication for positive social change is that other community colleges may be able to use the recommendations generated in the report to improve their learning community programs so that their students might be encouraged to persist towards degree completion.
23
Hospedales, Timothy. "Bayesian multisensory perception." Thesis, University of Edinburgh, 2008. http://hdl.handle.net/1842/2156.
Full textAbstract:
A key goal for humans and artificial intelligence systems is to develop an accurate and unified picture of the outside world based on the data from any sense(s) that may be available. The availability of multiple senses presents the perceptual system with new opportunities to fulfil this goal, but exploiting these opportunities first requires the solution of two related tasks. The first is how to make the best use of any redundant information from the sensors to produce the most accurate percept of the state of the world. The second is how to interpret the relationship between observations in each modality; for example, the correspondence problem of whether or not they originate from the same source. This thesis investigates these questions using ideal Bayesian observers as the underlying theoretical approach. In particular, the latter correspondence task is treated as a problem of Bayesian model selection or structure inference in Bayesian networks. This approach provides a unified and principled way of representing and understanding the perceptual problems faced by humans and machines and their commonality. In the domain of machine intelligence, we exploit the developed theory for practical benefit, developing a model to represent audio-visual correlations. Unsupervised learning in this model provides automatic calibration and user appearance learning, without human intervention. Inference in the model involves explicit reasoning about the association between latent sources and observations. This provides audio-visual tracking through occlusion with improved accuracy compared to standard techniques. It also provides detection, verification and speech segmentation, ultimately allowing the machine to understand ``who said what, where?'' in multi-party conversations. In the domain of human neuroscience, we show how a variety of recent results in multimodal perception can be understood as the consequence of probabilistic reasoning about the causal structure of multimodal observations. We show this for a localisation task in audio-visual psychophysics, which is very similar to the task solved by our machine learning system. We also use the same theory to understand results from experiments in the completely different paradigm of oddity detection using visual and haptic modalities. These results begin to suggest that the human perceptual system performs -- or at least approximates -- sophisticated probabilistic reasoning about the causal structure of observations under the hood.
24
Ozgen, Emre. "Language, learning, and colour categorisation." Thesis, University of Surrey, 2000. http://epubs.surrey.ac.uk/844210/.
Full textAbstract:
The relationship between language and colour categorisation is explored testing the predictions of the linguistic relativity hypothesis. The basic colour terms of Turkish are investigated, with findings suggesting that the Berlin and Kay (1969) theory of universal colour term evolution might require further revisions. The maximum number allowed by the theory is exceeded by the Turkish colour term inventory, by an extra term in the blue region. This difference between Turkish and English is exploited to test the effects of linguistic categories on colour perception and cognition. Evidence is presented suggesting that some aspects of categorical colour perception may not be fixed and universal, but flexible and culture-specific. Perceived similarity of colours seems to be open to influence by a linguistic category boundary. The argument of flexibility is further investigated using a category learning paradigm. Evidence suggested that perceptual and cognitive effects of colour category boundaries might be acquired through laboratory training. Subjects judge colours to be different more accurately when they come from different categories acquired in training than when they are from the same category. Mechanisms, which may be responsible for such flexibility, are explored in relation to findings in the literature. It is argued that perception and cognition may not be distinguished from each other by clear-cut boundaries. Rather, and interaction between percepts and concepts may facilitate effects of language and learning on human colour categorisation.
25
Bartlett, Marian Stewart. "Face image analysis by unsupervised learning and redundancy reduction /." Diss., Connect to a 24 p. preview or request complete full text in PDF format. Access restricted to UC campuses, 1998. http://wwwlib.umi.com/cr/ucsd/fullcit?p9907603.
Full text
26
Yeung, Fung-yi. "Academic, social and general self-concepts of students with learning disabilities." Hong Kong : University of Hong Kong, 2001. http://sunzi.lib.hku.hk:8888/cgi-bin/hkuto%5Ftoc%5Fpdf?B23476576.
Full text
27
Windridge, David, Michael Felsberg, and Affan Shaukat. "A Framework for Hierarchical Perception–Action Learning Utilizing Fuzzy Reasoning." Linköpings universitet, Datorseende, 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-85688.
Full textAbstract:
Perception-action (P-A) learning is an approach to cognitive system building that seeks to reduce the complexity associated with conventional environment-representation/action-planning approaches. Instead, actions are directly mapped onto the perceptual transitions that they bring about, eliminating the need for intermediate representation and significantly reducing training requirements. We here set out a very general learning framework for cognitive systems in which online learning of the P-A mapping may be conducted within a symbolic processing context, so that complex contextual reasoning can influence the P-A mapping. In utilizing a variational calculus approach to define a suitable objective function, the P-A mapping can be treated as an online learning problem via gradient descent using partial derivatives. Our central theoretical result is to demonstrate top-down modulation of low-level perceptual confidences via the Jacobian of the higher levels of a subsumptive P-A hierarchy. Thus, the separation of the Jacobian as a multiplying factor between levels within the objective function naturally enables the integration of abstract symbolic manipulation in the form of fuzzy deductive logic into the P-A mapping learning. We experimentally demonstrate that the resulting framework achieves significantly better accuracy than using P-A learning without top-down modulation. We also demonstrate that it permits novel forms of context-dependent multilevel P-A mapping, applying the mechanism in the context of an intelligent driver assistance system.DIPLECS
GARNICS
CUAS
28
Cervera, Mateu Enric. "Perception-Based Learning for Fine Motion Planning in Robot Manipulation." Doctoral thesis, Universitat Jaume I, 1997. http://hdl.handle.net/10803/10377.
Full textAbstract:
Robots must successfully execute tasks in the presence of uncertainty. The main sources of uncertainty are modeling, sensing, and control. Fine motion problems involve a small-scale space and contact between objects.
Though modern manipulators are very precise and repetitive, complex tasks may be difficult --or even impossible-- to model at the desired degree of exactitude; moreover, in real-world situations, the environment is not known a-priori and visual sensing does not provide enough accuracy.
In order to develop successful strategies, it is necessary to understand what can be perceived, what action can be learnt --associated-- according to the perception, and how can the robot optimize its actions with regard to defined criteria.
The thesis describes a robot programming architecture for learning fine motion tasks.
Learning is an autonomous process of experience repetition, and the target is to achieve the goal in the minimum number of steps. Uncertainty in the location is assumed, and the robot is guided mainly by the sensory information acquired by a force sensor.
The sensor space is analyzed by an unsupervised process which extracts features related with the probability distribution of the input samples. Such features are used to build a discrete state of the task to which an optimal action is associated, according to the past experience. The thesis also includes simulations of different sensory-based tasks to illustrate some aspects of the learning processes.
The learning architecture is implemented on a real robot arm with force sensing capabilities. The task is a peg-in-hole insertion with both cylindrical and non-cylindrical workpieces.
29
Han, Chung-wai Christina, and 韓重惠. "Teachers' perception of implementing computer assisted learning in kindergarten classrooms." Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 1997. http://hub.hku.hk/bib/B31959398.
Full text
30
Hammer, Lotte. "The role of creativity in teaching and learning : children's perception." Thesis, University of Exeter, 2002. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.248121.
Full text
31
Owen, Ann Lesley. "Development of tests of emotion-related learning in person perception." Thesis, Keele University, 2001. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.392158.
Full text
32
Saads, Silvia Maria Leao. "Learning about polyhedra through visual and tactile perception and discussion." Thesis, University of Southampton, 2000. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.326581.
Full text
33
Han, Chung-wai Christina. "Teachers' perception of implementing computer assisted learning in kindergarten classrooms." Hong Kong : University of Hong Kong, 1997. http://sunzi.lib.hku.hk/hkuto/record.jsp?B1882142X.
Full text
34
PINHEIRO, ROBERTO MEIRELES. "QUALITY PERCEPTION OF DISTANCE LEARNING THROUGH THE INTERNET : STUDY CASE." PONTIFÍCIA UNIVERSIDADE CATÓLICA DO RIO DE JANEIRO, 2002. http://www.maxwell.vrac.puc-rio.br/Busca_etds.php?strSecao=resultado&nrSeq=3985@1.
Full textAbstract:
A presente pesquisa teve por objetivo discutir como um dado
sistema de gerenciamento de EaD baseada na Internet pode
revelar aplicabilidade pedagógica a um determinado conteúdo
trabalhado a distância. Discutiu-se, também, de que
forma este tipo de sistema pode contribuir para uma
mediação pedagógica adequada dos conteúdos por ele
veiculados, bem como jogar algumas luzes sobre
as facilidades e dificuldades vivenciadas pelos seus
usuários. Finalmente, tivemos por objetivo discutir a
extensão e a direção do hiato de qualidade entre a proposta
dos autores e patrocinadores de uma iniciativa específica
de EaD baseada na Internet a e a qualidade percebida pelos
seus usuários. Logo após a Introdução, esta pesquisa
apresenta uma discussão sobre a Cibercultura e seus
reflexos sobre a Educação a Distância, confrontando
diferentes pontos de vista sobre o assunto. Prossegue-se
com uma análise da EaD baseada na Internet no Brasil e com
uma apresentação dos principais gerenciadores de EaD
baseada na Internet. Por fim, descreve-se brevemente o
Curso Pós-Médio em Informática da Fundação Bradesco,
realizado em convênio com a Cisco Systems do Brasil, sobre
o qual aplicou-se um modelo empírico de avaliação de
percepção de qualidade, a saber, o modelo ServQual,
proposto em 1985 por Parasuraman et al.. A dissertação
finaliza-se com algumas conclusões decorrentes do confronto
de visões dos diversos atores do processo, sugerindo
direções para pesquisa futura.The present research intends to discuss how a certain Internet Learning Management System may be pedagogicly applied to a content delivered at distance. It is also discussed how this kind of system may contribute to an adequate pedagogic mediation of the contents that it delivers. The work also spreads some light over the facilities and difficulties that its users face. The final goal is to discuss the extent and the direction of the quality gap between the authors and sponsors propositions of a given iniciative of Distance Learning though the Internet and the quality perceived by its users. Right after the Introduction, this research presents a discussion about the Cyberculture and its reflexions on the Distance Education, comparing different points of view about the subject. Then the Distance Learning through the Internet in Brazil is analysed, presenting the main learning management systems. Finaly, the Fundação Bradesco Computer Science Course is described, on which it was applied an empiric model of quality perception evaluation, the ServQual, created in 1985 by Parasuraman et al.. The research ends with some conclusions derived from the confrontation of points of view of the different actors involved, suggesting directions for future research.
35
Zheng, David Y. M. Eng Massachusetts Institute of Technology. "Unsupervised learning of latent physical properties using perception-prediction networks." Thesis, Massachusetts Institute of Technology, 2018. http://hdl.handle.net/1721.1/119693.
Full textAbstract:
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2018.This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
Cataloged from student-submitted PDF version of thesis.
Includes bibliographical references (pages 22-24).
We propose a framework for the completely unsupervised learning of latent object properties from their interactions: the perception-prediction network (PPN). Consisting of a perception module that extracts representations of latent object properties and a prediction module that uses those extracted properties to simulate system dynamics, the PPN can be trained in an end-to-end fashion purely from samples of object dynamics. We find that the representations of latent object properties learned by PPNs not only are sufficient to accurately simulate the dynamics of systems comprised of previously unseen objects, but also can be translated directly into human-interpretable properties (e.g. mass, coefficient of restitution) in an entirely unsupervised manner. Crucially, PPNs also generalize to novel scenarios: their gradient-based training can be applied to many dynamical systems and their graph-based structure functions over systems comprised of different numbers of objects. Our results demonstrate the efficacy of graph-based neural architectures in object-centric inference and prediction tasks, and our model has the potential to discover relevant object properties in systems that are not yet well understood.
by David Y. Zheng.
M. Eng.
36
Snyders, Hendrik. "A learning organisation perception survey of the Saldanha Bay Municipality." Thesis, Cape Peninsula University of Technology, 2008. http://hdl.handle.net/20.500.11838/975.
Full textAbstract:
Thesis (MTech (Business Administration))--Cape Peninsula University of Technology, 2008The merger of South African municipalities in the year 2000, and the dawn of the era of developmental local government, has confronted local authorities with a range of new challenges. In addition to the need to develop a new organisational culture and mutual trust, or the introduction of soft management actions, municipalities have to aetualise the concepts and processes of co-operative governance, integrated development planning, public participation and developmental local government. In addition, the White Paper on Local Government (WPLG, 1998) implores municipalities to lead and learn while they search for local solutions. An inability to learn and manage in a changed context and circumstances will inevitably lead to public displays of dissatisfaction, such as public demonstrations, that undermine municipalities' legitimacy. To overcome legitimacy dilemmas, municipalities need to strengthen their learning capabilities to enable them to operate effectively within changed circumstances and to become learning organisations. Such organisations, according to Senge (1990), have succeeded in formulating a shared vision, displayed a high level of personal mastery and team learning, as well as practising systems thinking. Together with these elements municipalities must identify and improve potentially constraining mental models. However, transforming any organisation into a learning organisation according to Dilworth (1996) requires a particular set of leadership qualities, such as commitment to the improvement of the quality of work life, democratic leadership and the promotion of human dignity. In this thesis, a learning organisation survey of the Saldanha Bay municipality's leadership cadre, consisting of Municipal Councillors, Executive Directors and Departmental Managers and Division Heads is undertaken with a view to determine whether these key functionaries practise the key learning disciplines of team leaming, shared vision, systems thinking, mental models and personal mastery. The results of this study indicated that the municipality in question has not yet succeeded in becoming a learning municipality. It has at best succeeded in laying a foundation for both councillors and officials to build on in order to achieve the desired result.
37
Garcia-Garcia, Alberto. "Deep Learning for 3D Perception: Computer Vision and Tactile Sensing." Doctoral thesis, Universidad de Alicante, 2019. http://hdl.handle.net/10045/103751.
Full textAbstract:
The care of dependent people (for reasons of aging, accidents, disabilities or illnesses) is one of the top priority lines of research for the European countries as stated in the Horizon 2020 goals. In order to minimize the cost and the intrusiveness of the therapies for care and rehabilitation, it is desired that such cares are administered at the patient’s home. The natural solution for this environment is an indoor mobile robotic platform. Such robotic platform for home care needs to solve to a certain extent a set of problems that lie in the intersection of multiple disciplines, e.g., computer vision, machine learning, and robotics. In that crossroads, one of the most notable challenges (and the one we will focus on) is scene understanding: the robot needs to understand the unstructured and dynamic environment in which it navigates and the objects with which it can interact. To achieve full scene understanding, various tasks must be accomplished. In this thesis we will focus on three of them: object class recognition, semantic segmentation, and grasp stability prediction. The first one refers to the process of categorizing an object into a set of classes (e.g., chair, bed, or pillow); the second one goes one level beyond object categorization and aims to provide a per-pixel dense labeling of each object in an image; the latter consists on determining if an object which has been grasped by a robotic hand is in a stable configuration or if it will fall. This thesis presents contributions towards solving those three tasks using deep learning as the main tool for solving such recognition, segmentation, and prediction problems. All those solutions share one core observation: they all rely on tridimensional data inputs to leverage that additional dimension and its spatial arrangement. The four main contributions of this thesis are: first, we show a set of architectures and data representations for 3D object classification using point clouds; secondly, we carry out an extensive review of the state of the art of semantic segmentation datasets and methods; third, we introduce a novel synthetic and large-scale photorealistic dataset for solving various robotic and vision problems together; at last, we propose a novel method and representation to deal with tactile sensors and learn to predict grasp stability.
38
Eastman, Elizabeth Merritt. "Deep learning models for the perception of human social interactions." Thesis, Massachusetts Institute of Technology, 2019. https://hdl.handle.net/1721.1/123019.
Full textAbstract:
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019
Cataloged from student-submitted PDF version of thesis.
Includes bibliographical references (pages 59-61).
Social interaction perception is an important part of humans' visual experience. How- ever, little is known about the way the human brain processes visual input in order to understand social interactions. In comparison, other vision problems, such as object recognition tasks, have been studied extensively and seen success by comparing state of the art computer vision models to neuroimaging data. In this thesis, I employ a similar method in order to study social interaction perception with deep learning models and magnetoencephalography (MEG) data. Specically, I implement dierent deep learning computer vision models and test their performance on a social inter- action detection task as well as their match to neural data from the same task. I nd that detecting social interactions most likely requires extensive cortical process- ing and/or recurrent computations. In addition, I nd that experience with action recognition does not improve social interaction detection.
by Elizabeth Merritt Eastman.
M. Eng.
M.Eng. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science
39
Reichlin, Alfredo. "Perception Learning For Deep Visuomotor Control Of A Robotic Arm." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-276679.
Full textAbstract:
This thesis studies the problem of estimating the necessary information about the environment in order to make a robotic arm being able to learn autonomously simple control tasks. The state is estimated from a stream of images using a deep neural network. The network is divided into two models that estimate the state in parallel. The first one is an autoencoder like network that maps images to the states. The second one is a simple prediction model that infers the state from the previous one. On top of that, a model is proposed to estimate the uncertainty for each feature of the state estimated from the images. The two estimated states are joined together with this uncertainty measure to give a single robust state of the environment. To assess the performances of the models, a number of experiments are conducted in a simulation environment. Results show that a representation learned with this model is generally more robust to visual occlusion in the images. Finally, the estimated state is used to learn a control policy for the robotic arm to perform a simple task using reinforcement learning.Denna uppsats studerar problemet att approximera nödvändig information om omgivningen för att låta en robotarm autonomt lära sig utföra enkla kontroll- uppgifter. Denna information, det så kallade tillståndet, estimeras från en ström av bilder med hjälp av ett djupt neuralt nätverk. Nätverket är indelat i två modeller som uppskattar tillståndet parallellt. Det första är ett nätverk liknande en autoencoder som direkt mappar bilder till tillstånden. Den andra relativt enkla modellen predikterar direkt ett tillstånd från det föregående. Utöver detta föreslås en modell för att uppskatta osäkerheten för varje element i tillståndet som är beräknat från bilderna. De två approximationerna förenas till en enda robust uppskattning av tillståndet med hjälp av osäkerhetsmåttet. För att utvärdera modellerna utförs ett antal experiment i en simuleringsmiljö. Resultaten visar att representationen av tillståndet som modellen lärt sig i allmänhet är mer robust för visuellt blockerad information i bilderna. Slutligen används det uppskattade tillståndet i kombination med reinforcement learning för att lära robotarmen en kontrollpolicy för att utföra en enkel uppgift.
40
Laerhoven, Kristof van. "Embedded perception : concept recognition by learning and combining sensory data." Thesis, Lancaster University, 2006. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.443519.
Full text
41
Norris, Sheila J. "Workplace learning, an assessment of approaches to learning and perception of the learning environment in two public health organisations." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1998. http://www.collectionscanada.ca/obj/s4/f2/dsk2/ftp01/MQ36066.pdf.
Full text
42
Jaime, Mark. "The Role of Temporal Synchrony in the Facilitation of Perceptual Learning during Prenatal Development." FIU Digital Commons, 2007. http://digitalcommons.fiu.edu/etd/58.
Full textAbstract:
This study explored the critical features of temporal synchrony for the facilitation of prenatal perceptual learning with respect to unimodal stimulation using an animal model, the bobwhite quail. The following related hypotheses were examined: (1) the availability of temporal synchrony is a critical feature to facilitate prenatal perceptual learning, (2) a single temporally synchronous note is sufficient to facilitate prenatal perceptual learning, with respect to unimodal stimulation, and (3) in situations where embryos are exposed to a single temporally synchronous note, facilitated perceptual learning, with respect to unimodal stimulation, will be optimal when the temporally synchronous note occurs at the onset of the stimulation bout. To assess these hypotheses, two experiments were conducted in which quail embryos were exposed to various audio-visual configurations of a bobwhite maternal call and tested at 24 hr after hatching for evidence of facilitated prenatal perceptual learning with respect to unimodal stimulation. Experiment 1 explored if intermodal equivalence was sufficient to facilitate prenatal perceptual learning with respect to unimodal stimulation. A Bimodal Sequential Temporal Equivalence (BSTE) condition was created that provided embryos with sequential auditory and visual stimulation in which the same amodal properties (rate, duration, rhythm) were made available across modalities. Experiment 2 assessed: (a) whether a limited number of temporally synchronous notes are sufficient for facilitated prenatal perceptual learning with respect to unimodal stimulation, and (b) whether there is a relationship between timing of occurrence of a temporally synchronous note and the facilitation of prenatal perceptual learning. Results revealed that prenatal exposure to BSTE was not sufficient to facilitate perceptual learning. In contrast, a maternal call that contained a single temporally synchronous note was sufficient to facilitate embryos’ prenatal perceptual learning with respect to unimodal stimulation. Furthermore, the most salient prenatal condition was that which contained the synchronous note at the onset of the call burst. Embryos’ prenatal perceptual learning of the call was four times faster in this condition than when exposed to a unimodal call. Taken together, bobwhite quail embryos’ remarkable sensitivity to temporal synchrony suggests that this amodal property plays a key role in attention and learning during prenatal development.
43
Crook, Paul A. "Learning in a state of confusion : employing active perception and reinforcement learning in partially observable worlds." Thesis, University of Edinburgh, 2007. http://hdl.handle.net/1842/1471.
Full textAbstract:
In applying reinforcement learning to agents acting in the real world we are often faced with tasks that are non-Markovian in nature. Much work has been done using state estimation algorithms to try to uncover Markovian models of tasks in order to allow the learning of optimal solutions using reinforcement learning. Unfortunately these algorithms which attempt to simultaneously learn a Markov model of the world and how to act have proved very brittle. Our focus differs. In considering embodied, embedded and situated agents we have a preference for simple learning algorithms which reliably learn satisficing policies. The learning algorithms we consider do not try to uncover the underlying Markovian states, instead they aim to learn successful deterministic reactive policies such that agents actions are based directly upon the observations provided by their sensors. Existing results have shown that such reactive policies can be arbitrarily worse than a policy that has access to the underlying Markov process and in some cases no satisficing reactive policy can exist. Our first contribution is to show that providing agents with alternative actions and viewpoints on the task through the addition of active perception can provide a practical solution in such circumstances. We demonstrate empirically that: (i) adding arbitrary active perception actions to agents which can only learn deterministic reactive policies can allow the learning of satisficing policies where none were originally possible; (ii) active perception actions allow the learning of better satisficing policies than those that existed previously and (iii) our approach converges more reliably to satisficing solutions than existing state estimation algorithms such as U-Tree and the Lion Algorithm. Our other contributions focus on issues which affect the reliability with which deterministic reactive satisficing policies can be learnt in non-Markovian environments. We show that that greedy action selection may be a necessary condition for the existence of stable deterministic reactive policies on partially observable Markov decision processes (POMDPs). We also set out the concept of Consistent Exploration. This is the idea of estimating state-action values by acting as though the policy has been changed to incorporate the action being explored. We demonstrate that this concept can be used to develop better algorithms for learning reactive policies to POMDPs by presenting a new reinforcement learning algorithm; the Consistent Exploration Q(l) algorithm (CEQ(l)). We demonstrate on a significant number of problems that CEQ(l) is more reliable at learning satisficing solutions than the algorithm currently regarded as the best for learning deterministic reactive policies, that of SARSA(l).
44
Radjaeipour, Gitta. "The accuracy of dental students' perception of their learning in relation to their actual conceptual learning." Scholarly Commons, 2009. https://scholarlycommons.pacific.edu/uop_etds/2392.
Full textAbstract:
Dental schools are faced with the challenge of incorporating varied instructional methodologies into their curriculum. Various dental schools distinguish different modules in their program under preclinical and clinical disciplines with minimal connections between the two. This study investigated students' perceptions of their curriculum and, more specifically, compare and contrast dental students' perceptions of learning during the first or freshman years, the second or junior years, and the third years as seniors in 2005, 2006, and 2007. It contrasts the results from students' perceptions and students' actual learning to establish correlations between these two phenomena. Various standard assessments were used. Students' understanding of the use of dental materials including base, liner, and cement were measured as predicting factors to substantiate the accuracy of the students' perceptions. A questionnaire was used to elicit a total of 853 responses over the three consecutive years. Pearson correlations were applied to analyze the data. The main finding was a positive correlation between the accuracy of students perceptions of learning and their participation in clinical practice; whereas no correlation was confirmed with regard to the accuracy of students' perceptions of learning when students had only or primarily participated in preclinical courses. The results suggest that advanced students' perceptions and knowledge can be considered by faculty when making decisions regarding reform of their dental curriculum
45
Zapata-Impata, Brayan S. "Robotic manipulation based on visual and tactile perception." Doctoral thesis, Universidad de Alicante, 2020. http://hdl.handle.net/10045/118217.
Full textAbstract:
We still struggle to deliver autonomous robots that perform manipulation tasks as simple for a human as picking up items. A portion of the difficulty of this task lays on the fact that such operation requires a robot that can deal with uncertainty in an unstructured environment. We propose in this thesis the use of visual and tactile perception for providing solutions that can improve the robustness of a robotic manipulator in such environment. In this thesis, we approach robotic grasping using a single 3D point cloud with a partial view of the objects present in the scene. Moreover, the objects are unknown: they have not been previously recognised and we do not have a 3D model to compute candidate grasping points. In experimentation, we prove that our solution is fast and robust, taking in average 17 ms to find a grasp which is stable 85% of the time. Tactile sensors provide a rich source of information regarding the contact experienced by a robotic hand during the manipulation of an object. In this thesis, we exploit with deep learning this type of data for approaching the prediction of the stability of a grasp and the detection of the direction of slip of a contacted object. We prove that our solutions could correctly predict stability 76% of the time with a single tactile reading. We also demonstrate that learning temporal and spatial patterns leads to detections of the direction of slip which are correct up to 82% of the time and are only delayed 50 ms after the actual slip event begins. Despite the good results achieved on the previous two tactile tasks, this data modality has a serious flaw: it can only be registered during contact. In contrast, humans can estimate the feeling of grasping an object just by looking at it. Inspired by this, we present in this thesis our contributions for learning to generate tactile responses from vision. We propose a supervised solution based on training a deep neural network that models the behaviour of a tactile sensor, given 3D visual information of the target object and grasp data as an input. As a result, our system has to learn to link vision to touch. We prove in experimentation that our system learns to generate tactile responses on a set of 12 items, being off by only 0.06 relative error points. Furthermore, we also experiment with a semi-supervised solution for learning this task with a reduced need of labelled data. In experimentation, we show that it learns our tactile data generation task with 50% less data than the supervised solution, incrementing only 17% the error. Last, we introduce our work in the generation of candidate grasps which are improved through simulation of the tactile responses they would generate. This work unifies the contributions presented in this thesis, as it applies modules on calculating grasps, stability prediction and tactile data generation. In early experimentation, it finds grasps which are more stable than the original ones produced by our method based on 3D point clouds.This doctoral thesis has been carried out with the support of the Spanish Ministry of Economy, Industry and Competitiveness through the grant BES-2016-078290.
46
Leboe, Jason P. Milliken Bruce. "The inferential basis of perceptual performance /." *McMaster only, 2002.
Find full text
47
Ostroff, Wendy Louise. "Non-linguistic Influences on Infants' Nonnative Phoneme Perception: Exaggerated prosody and Visual Speech Information Aid Discrimination." Diss., Virginia Tech, 2000. http://hdl.handle.net/10919/27640.
Full textAbstract:
Research indicates that infants lose the capacity to perceive distinctions in nonnative sounds as they become sensitive to the speech sounds of their native language (i.e., by 10- to 12-months of age). However, investigations into the decline in nonnative phonetic perception have neglected to examine the role of non-linguistic information. Exaggerated prosodic intonation and facial input are prominent in the infantsâ language-learning environment, and both have been shown to ease the task of speech perception. The current investigation was designed to examine the impact of infant-directed (ID) speech and facial input on infantsâ ability to discriminate phonemes that do not contrast in their native language. Specifically, 11-month-old infants were tested for discrimination of both a native phoneme contrast and a nonnative phoneme contrast across four conditions, including an auditory manipulation (ID speech vs. AD speech) and a visual manipulation (Face vs. Geometric Form). The results indicated that infants could discriminate the native phonemes across any of the four conditions. Furthermore, the infants could discriminate the nonnative phonemes if they had enhanced auditory and visual information available to them (i.e., if they were presented in ID speech with a synchronous facial display), and if the nonnative discrimination task was the infantsâ first test session. These results suggest that infants do not lose the capacity to discriminate nonnative phonemes by the end of the first postnatal year, but that they rely on certain language-relevant and non-linguistic sources of information to discriminate nonnative sounds.Ph. D.
48
Kenny, Sarah. "Care staff perceptions of adults with profound learning disabilities : contents and processes." Thesis, Open University, 2000. http://oro.open.ac.uk/58060/.
Full textAbstract:
Background and Aims This research dissertation attempts to elicit care staff perceptions of clients with profound learning disabilities and the processes involved in these perceptions. There is little research in the area of staff perspectives in this field. Clinical psychologists working in this field often have extensive contact with staff regarding clients, and conflict regarding perception of clients can arise. It is suggested that for psychologists to gain some insight into how staff perceive clients and the processes involved would help to facilitate understanding of, and co-operation, with care staff. Design and Participants A qualitative design was employed as the study was seen as exploratory and was investigating the personal experiences and perspectives of participants. Participants were nine direct care staff who worked in a variety of service settings. Measures Each respondent completed a written free response description of a client of their choice. This was followed by a semi-structured interview that aimed to explore the processes involved in staff perceptions of clients. Results Written descriptions shared some factors in common with free response description within the general population. However, novel categories included communication issues, behavioural difficulties and the disability itself The interviews suggested that there were complex processes operating that made it difficult for respondents to acknowledge the disability and still feel positive about the clients and the work. There was also a marked change over time described by respondents in their perceptions of clients. Implications It is suggested care staff need a forum for acknowledging and exploring difficult feelings. Clinical psychologists are well placed to facilitate this but must also be aware of their own problems regarding acknowledging and coping with profound disability. Awareness of the issues might also help psychologists to work more sensitively and productively with staff.
49
Bondugula, Rajkumar. "Capturing the user's perception of directional spatial relations /." free to MU campus, to others for purchase, 2003. http://wwwlib.umi.com/cr/mo/fullcit?p1418006.
Full text
50
Weintraub, Gerald A. "Perception of control and coping mechanisms of children with learning disabilities." Thesis, McGill University, 1997. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=35648.
Full textAbstract:
Coping behaviour, perceived control, and the self concept of elementary school children with learning disabilities educated in regular and special education classrooms was examined using a comparative design. In addition, the influence of teachers' classroom management orientation on children's self-perceptions and coping behaviour was investigated. Children attending a special school for students with learning disabilities were found to be more adaptive copers than children in special education classes in regular schools, children receiving resource room assistance, and children mainstreamed in regular classes. Children with learning disabilities were found to have positive perceptions of their global self-worth regardless of the type of class they were in, although they indicated less confidence in their academic abilities compared to their self-perceptions of physical appearance and athletic competence. In general, most children believed that they were responsible for their academic successes and at the same time perceived academic failure as unavoidable. The students who coped most effectively demonstrated the most realistic appraisals of their academic situation. They recognized that they could not control academic failure, however, they believed that the best way to succeed in school was by continuing to exert effort. Additionally, successful copers held high expectations for future academic success and believed that they possessed the capacities needed to achieve this success. Children who coped most effectively strongly endorsed beliefs in their capacity to have a positive relationship with their teachers. Children who were rated as effective copers had teachers whose instructional orientation promoted autonomous functioning in their students.