Reducing state updates via Gaussian-gated LSTMs

Abstract

Recurrent neural networks can be difficult to train on long sequence data due to the well-known vanishing gradient problem. Some architectures incorporate methods to reduce RNN state updates, therefore allowing the network to preserve memory over long temporal intervals. To address these problems of convergence, this paper proposes a timing-gated LSTM RNN model, called the Gaussian-gated LSTM (g-LSTM). The time gate controls when a neuron can be updated during training, enabling longer memory persistence and better error-gradient flow. This model captures long-temporal dependencies better than an LSTM and the time gate parameters can be learned even from non-optimal initialization values. Because the time gate limits the updates of the neuron state, the number of computes needed for the network update is also reduced. By adding a computational budget term to the training loss, we can obtain a network which further reduces the number of computes by at least 10x. Finally, by employing a temporal curriculum learning schedule for the g-LSTM, we can reduce the convergence time of the equivalent LSTM network on long sequences.

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• Deep Learning in Neural Networks: An Overview
• A Critical Review of Recurrent Neural Networks for Sequence Learning
• Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences
• Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations
• Can recurrent neural networks warp time?