The huge size of deep networks hinders their use in small computing devices. In this paper, we consider compressing the network by weight quantization. We extend a recently proposed loss-aware weight binarization scheme to ternarization, with possibly different scaling parameters for the positive and negative weights, and m-bit (where m > 2) quantization. Experiments on feedforward and recurrent neural networks show that the proposed scheme outperforms state-of-the-art weight quantization algorithms, and is as accurate (or even more accurate) than the full-precision network.
@article{arxiv.1802.08635,
title = {Loss-aware Weight Quantization of Deep Networks},
author = {Lu Hou and James T. Kwok},
journal= {arXiv preprint arXiv:1802.08635},
year = {2018}
}