PredNet - "Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning" [code]

TitlePredNet - "Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning" [code]
Publication TypeCode
Year of Publication2016
AuthorsLotter, W, Kreiman, G, Cox, D
Abstract

The PredNet is a deep convolutional recurrent neural network inspired by the principles of predictive coding from the neuroscience literature [1, 2]. It is trained for next-frame video prediction with the belief that prediction is an effective objective for unsupervised (or "self-supervised") learning [e.g. 3-11].


For full project information and links to download code, etc. visit the website - https://coxlab.github.io/prednet/

Citation Key2882

Research Area: 

CBMM Relationship: 

  • CBMM Related