Encoding Longer-Term Contextual Information with Predictive Coding and Ego-Motion

Junpei Zhong*, Angelo Cangelosi, Tetsuya Ogata, Xinzheng Zhang

*この研究の対応する著者

研究成果: Article査読

3 被引用数 (Scopus)

抄録

Studies suggest that, within the hierarchical architecture, the topological higher level possibly represents the scenarios of the current sensory events with slower changing activities. They attempt to predict the neural activities on the lower level by relaying the predicted information after the scenario of the sensorimotor event has been determined. On the other hand, the incoming sensory information corrects such prediction of the events on the higher level by the fast-changing novel or surprising signal. From this point, we propose a predictive hierarchical artificial neural network model that examines this hypothesis on neurorobotic platforms. It integrates the perception and action in the predictive coding framework. Moreover, in this neural network model, there are different temporal scales of predictions existing on different levels of the hierarchical predictive coding architecture, which defines the temporal memories in recording the events occurring. Also, both the fast- and the slow-changing neural activities are modulated by the motor action. Therefore, the slow-changing neurons can be regarded as the representation of the recent scenario which the sensorimotor system has encountered. The neurorobotic experiments based on the architecture were also conducted.

本文言語English
論文番号7609587
ジャーナルComplexity
2018
DOI
出版ステータスPublished - 2018

ASJC Scopus subject areas

  • コンピュータ サイエンス(全般)
  • 一般

フィンガープリント

「Encoding Longer-Term Contextual Information with Predictive Coding and Ego-Motion」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル