A Neurally-Inspired Hierarchical Prediction Network for Spatiotemporal Sequence Learning and Prediction release_jlgyi2kt3vgo7iyudbu3oac67y

by Jielin Qiu, Ge Huang, Tai Sing Lee

Released as a article .

2019  

Abstract

In this paper we developed a hierarchical network model, called Hierarchical Prediction Network (HPNet), to understand how spatiotemporal memories might be learned and encoded in the recurrent circuits in the visual cortical hierarchy for predicting future video frames. This neurally inspired model operates in the analysis-by-synthesis framework. It contains a feed-forward path that computes and encodes spatiotemporal features of successive complexity and a feedback path for the successive levels to project their interpretations to the level below. Within each level, the feed-forward path and the feedback path intersect in a recurrent gated circuit, instantiated in a LSTM module, to generate a prediction or explanation of the incoming signals. The network learns its internal model of the world by minimizing the errors of its prediction of the incoming signals at each level of the hierarchy. We found that hierarchical interaction in the network increases semantic clustering of global movement patterns in the population codes of the units along the hierarchy, even in the earliest module. This facilitates the learning of relationships among movement patterns, yielding state-of-the-art performance in long range video sequence predictions in the benchmark datasets. The network model automatically reproduces a variety of prediction suppression and familiarity suppression neurophysiological phenomena observed in the visual cortex, suggesting that hierarchical prediction might indeed be an important principle for representational learning in the visual cortex.
In text/plain format

Archived Files and Locations

application/pdf  1.9 MB
file_ratc7loopraq7nkkfjph7do3ly
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2019-01-25
Version   v1
Language   en ?
arXiv  1901.09002v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 1728b745-5ba0-403c-936d-7517225f1bd0
API URL: JSON