How can a recurrent neurodynamic predictive coding model cope with fluctuation in temporal patterns? Robotic experiments on imitative interaction

Cited 3 time in webofscience Cited 0 time in scopus
  • Hit : 237
  • Download : 0
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.
Publisher
PERGAMON-ELSEVIER SCIENCE LTD
Issue Date
2017-08
Language
English
Article Type
Article
Keywords

SELF-ORGANIZATION; MIRROR SYSTEM; BEHAVIOR; IMAGERY; CORTEX; BRAIN

Citation

NEURAL NETWORKS, v.92, pp.3 - 16

ISSN
0893-6080
DOI
10.1016/j.neunet.2017.02.015
URI
http://hdl.handle.net/10203/225071
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 3 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0