Reduced-Gate Convolutional LSTM Design Using Predictive Coding for Next-Frame Video Prediction

Abstract

Spatiotemporal sequence prediction is an important problem in deep learning. We study next-frame video prediction using a deep-learning-based predictive coding framework that uses convolutional, long short-term memory (convLSTM) modules. We introduce a novel reduced-gate convolutional LSTM architecture. Our reduced-gate model achieves better next-frame prediction accuracy than the original convolutional LSTM while using a smaller parameter budget, thereby reducing training time. We tested our reduced gate modules within a predictive coding architecture on the moving MNIST and KITTI datasets. We found that our reduced-gate model has a significant reduction of approximately 40 percent of the total number of training parameters and training time in comparison with the standard LSTM model which makes it attractive for hardware implementation especially on small devices.

Tasks

Reproductions