Reduced-Gate Convolutional LSTM Using Predictive Coding for Spatiotemporal Prediction

TL;DR

This paper introduces a reduced-gate convolutional LSTM architecture that maintains or improves spatiotemporal prediction accuracy while significantly reducing parameters and training time, making it suitable for resource-constrained devices.

Contribution

The paper proposes a novel reduced-gate convLSTM that lowers parameter count and training time without sacrificing accuracy, advancing efficient spatiotemporal prediction models.

Findings

40% reduction in training parameters

25% decrease in training time

Improved prediction accuracy

Abstract

Spatiotemporal sequence prediction is an important problem in deep learning. We study next-frame(s) 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(rgcLSTM) architecture that requires a significantly lower parameter budget than a comparable convLSTM. By using a single multi-function gate, our reduced-gate model achieves equal or better next-frame(s) prediction accuracy than the original convolutional LSTM while using a smaller parameter budget, thereby reducing training time and memory requirements. 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 a 25 percent reduction in elapsed training time in comparison with the standard convolutional LSTM model. The performance accuracy of the new model was also improved. This makes our model more attractive for hardware implementation, especially on small devices. We also explored a space of twenty different gated architectures to get insight into how our rgcLSTM fit into that space.