Predictive coding for dynamic vision: Development of functional hierarchy in a multiple spatio-temporal scales RNN model

Cited 2 time in webofscience Cited 0 time in scopus
  • Hit : 33
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorChoi, Minkyuko
dc.contributor.authorTani, Junko
dc.date.accessioned2023-08-04T05:01:12Z-
dc.date.available2023-08-04T05:01:12Z-
dc.date.created2023-07-07-
dc.date.created2023-07-07-
dc.date.issued2017-05-
dc.identifier.citation2017 International Joint Conference on Neural Networks, IJCNN 2017, pp.657 - 664-
dc.identifier.urihttp://hdl.handle.net/10203/311163-
dc.description.abstractThe current paper presents a novel recurrent neural network model, predictive multiple spatio-temporal scales RNN (P-MSTRNN), which can generate as well as recognize dynamic visual patterns in a predictive coding framework. The model is characterized by multiple spatio-temporal scales imposed on neural unit dynamics through which an adequate spatio-temporal hierarchy develops via learning from exemplars. The model was evaluated by conducting an experiment of learning a set of whole body human movement patterns, which was generated by following a hierarchically defined movement syntax. The analysis of the trained model clarifies what types of spatio-temporal hierarchy develops in dynamic neural activity as well as how robust generation and recognition of movement patterns can be achieved by using the error minimization principle.-
dc.languageEnglish-
dc.publisherInstitute of Electrical and Electronics Engineers Inc.-
dc.titlePredictive coding for dynamic vision: Development of functional hierarchy in a multiple spatio-temporal scales RNN model-
dc.typeConference-
dc.identifier.wosid000426968700088-
dc.identifier.scopusid2-s2.0-85030991444-
dc.type.rimsCONF-
dc.citation.beginningpage657-
dc.citation.endingpage664-
dc.citation.publicationname2017 International Joint Conference on Neural Networks, IJCNN 2017-
dc.identifier.conferencecountryUS-
dc.identifier.conferencelocationAnchorage, AK-
dc.identifier.doi10.1109/IJCNN.2017.7965915-
dc.contributor.localauthorTani, Jun-
dc.contributor.nonIdAuthorChoi, Minkyu-
Appears in Collection
EE-Conference Papers(학술회의논문)
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 2 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0