Exploiting Spatio-Temporal Structure With Recurrent Winner-Take-All Networks.

Abstract

We propose a convolutional recurrent neural network (ConvRNNs), with winner-take-all (WTA) dropout for high-dimensional unsupervised feature learning in multidimensional time series. We apply the proposed method for object recognition using temporal context in videos and obtain better results than comparable methods in the literature, including the deep predictive coding networks (DPCNs) previously proposed by Chalasani and Principe. Our contributions can be summarized as a scalable reinterpretation of the DPCNs trained end-to-end with backpropagation through time, an extension of the previously proposed WTA autoencoders to sequences in time, and a new technique for initializing and regularizing ConvRNNs.