Recurrent Neural Networks With Limited Numerical Precision
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.
Code (1)
Tasks
BinarizationSimilar Papers 제목 키워드 기반
Recurrent Neural Networks With Limited Numerical Precision
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 intere…
QuantizationMixed Precision Training
Deep neural networks have enabled progress in a wide variety of applications. Growing the size of the neural network typically results in improved accuracy. As model sizes grow, the memory and compute requirements for tr…
Curvature-aware dynamic precision approach for physics-informed neural networks
Physics-informed neural networks (PINNs) have become a promising framework for simulating partial differential equations (PDEs) by embedding physical laws directly into neural network training. However, recent studies sh…
Computational EfficiencyAnalytical Guarantees on Numerical Precision of Deep Neural Networks
The acclaimed successes of neural networks often overshadow their tremendous complexity. We focus on numerical precision – a key parameter defining the complexity of neural networks. First, we present theoretical bo…
HitNet: Hybrid Ternary Recurrent Neural Network
Quantization is a promising technique to reduce the model size, memory footprint, and massive computation operations of recurrent neural networks (RNNs) for embedded devices with limited resources. Although extreme low-b…
Quantization