Exploiting Spatio-Temporal Structure with Recurrent Winner-Take-All Networks
arXiv:1611.00050
Abstract
We propose a convolutional recurrent neural network, with Winner-Take-All dropout for high dimensional unsupervised feature learning in multi-dimensional time series. We apply the proposedmethod for object recognition with temporal context in videos and obtain better results than comparable methods in the literature, including the Deep Predictive Coding Networks previously proposed by Chalasani and Principe.Our contributions can be summarized as a scalable reinterpretation of the Deep Predictive Coding Networks trained end-to-end with backpropagation through time, an extension of the previously proposed Winner-Take-All Autoencoders to sequences in time, and a new technique for initializing and regularizing convolutional-recurrent neural networks.
arXiv commentunder review
References in corpus (12)
- Adam: A Method for Stochastic Optimization
- Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
- Improving neural networks by preventing co-adaptation of feature detectors
- Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning
- Spatio-temporal video autoencoder with differentiable memory
- Unsupervised Learning of Visual Representations using Videos
- Winner-Take-All Autoencoders
- Learning Spatiotemporal Features with 3D Convolutional Networks
- Learning to See by Moving
- Multi-task Sequence to Sequence Learning
- Deep Predictive Coding Networks
- Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles