DC Field | Value | Language |
---|---|---|
dc.contributor.author | Ahmadi, Ahmadreza | ko |
dc.contributor.author | Tani, Jun | ko |
dc.date.accessioned | 2017-08-08T06:04:54Z | - |
dc.date.available | 2017-08-08T06:04:54Z | - |
dc.date.created | 2017-07-17 | - |
dc.date.created | 2017-07-17 | - |
dc.date.issued | 2017-08 | - |
dc.identifier.citation | NEURAL NETWORKS, v.92, pp.3 - 16 | - |
dc.identifier.issn | 0893-6080 | - |
dc.identifier.uri | http://hdl.handle.net/10203/225071 | - |
dc.description.abstract | The current paper examines how a recurrent neural network (RNN) model using a dynamic predictive coding scheme can cope with fluctuations in temporal patterns through generalization in learning. The conjecture driving this present inquiry is that a RNN model with multiple timescales (MTRNN) learns by extracting patterns of change from observed temporal patterns, developing an internal dynamic structure such that variance in initial internal states account for modulations in corresponding observed patterns. We trained a MTRNN with low-dimensional temporal patterns, and assessed performance on an imitation task employing these patterns. Analysis reveals that imitating fluctuated patterns consists in inferring optimal internal states by error regression. The model was then tested through humanoid robotic experiments requiring imitative interaction with human subjects. Results show that spontaneous and lively interaction can be achieved as the model successfully copes with fluctuations naturally occurring in human movement patterns. (C) 2017 Elsevier Ltd. All rights reserved. | - |
dc.language | English | - |
dc.publisher | PERGAMON-ELSEVIER SCIENCE LTD | - |
dc.subject | SELF-ORGANIZATION | - |
dc.subject | MIRROR SYSTEM | - |
dc.subject | BEHAVIOR | - |
dc.subject | IMAGERY | - |
dc.subject | CORTEX | - |
dc.subject | BRAIN | - |
dc.title | How can a recurrent neurodynamic predictive coding model cope with fluctuation in temporal patterns? Robotic experiments on imitative interaction | - |
dc.type | Article | - |
dc.identifier.wosid | 000404505600002 | - |
dc.identifier.scopusid | 2-s2.0-85016593348 | - |
dc.type.rims | ART | - |
dc.citation.volume | 92 | - |
dc.citation.beginningpage | 3 | - |
dc.citation.endingpage | 16 | - |
dc.citation.publicationname | NEURAL NETWORKS | - |
dc.identifier.doi | 10.1016/j.neunet.2017.02.015 | - |
dc.contributor.localauthor | Tani, Jun | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Neuro-robotics | - |
dc.subject.keywordAuthor | Predictive coding | - |
dc.subject.keywordAuthor | Recurrent neural networks | - |
dc.subject.keywordAuthor | Synchronized imitation | - |
dc.subject.keywordAuthor | Time-warping | - |
dc.subject.keywordAuthor | Error regression | - |
dc.subject.keywordPlus | SELF-ORGANIZATION | - |
dc.subject.keywordPlus | MIRROR SYSTEM | - |
dc.subject.keywordPlus | BEHAVIOR | - |
dc.subject.keywordPlus | IMAGERY | - |
dc.subject.keywordPlus | CORTEX | - |
dc.subject.keywordPlus | BRAIN | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.