Recurrent Neural Networks With Limited Numerical Precision

TL;DR

This paper investigates methods for reducing numerical precision in RNN training, finding that certain ternarization techniques can maintain or improve accuracy, thus enabling more efficient hardware implementations.

Contribution

It introduces and evaluates stochastic and deterministic ternarization methods for low-precision RNN training, extending prior work beyond CNNs and fully-connected networks.

Findings

Weight binarization does not work well with RNNs.

Ternarization methods can achieve comparable or higher accuracy.

Low-precision RNNs enable more efficient hardware implementations.

Abstract

Recurrent Neural Networks (RNNs) produce state-of-art performance on many machine learning tasks but their demand on resources in terms of memory and computational power are often high. Therefore, there is a great interest in optimizing the computations performed with these models especially when considering development of specialized low-power hardware for deep networks. One way of reducing the computational needs is to limit the numerical precision of the network weights and biases. This has led to different proposed rounding methods which have been applied so far to only Convolutional Neural Networks and Fully-Connected Networks. This paper addresses the question of how to best reduce weight precision during training in the case of RNNs. We present results from the use of different stochastic and deterministic reduced precision training methods applied to three major RNN types which are then tested on several datasets. The results show that the weight binarization methods do not work with the RNNs. However, the stochastic and deterministic ternarization, and pow2-ternarization methods gave rise to low-precision RNNs that produce similar and even higher accuracy on certain datasets therefore providing a path towards training more efficient implementations of RNNs in specialized hardware.