Quantized neural network design under weight capacity constraint

Autor:	Shin, Sungho, Hwang, Kyuyeon, Sung, Wonyong
Rok vydání:	2016
Předmět:	Computer Science - Learning Computer Science - Neural and Evolutionary Computing
Druh dokumentu:	Working Paper
Popis:	The complexity of deep neural network algorithms for hardware implementation can be lowered either by scaling the number of units or reducing the word-length of weights. Both approaches, however, can accompany the performance degradation although many types of research are conducted to relieve this problem. Thus, it is an important question which one, between the network size scaling and the weight quantization, is more effective for hardware optimization. For this study, the performances of fully-connected deep neural networks (FCDNNs) and convolutional neural networks (CNNs) are evaluated while changing the network complexity and the word-length of weights. Based on these experiments, we present the effective compression ratio (ECR) to guide the trade-off between the network size and the precision of weights when the hardware resource is limited. Comment: This paper is accepted at NIPS 2016 workshop on Efficient Methods for Deep Neural Networks (EMDNN). arXiv admin note: text overlap with arXiv:1511.06488
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1611.06342 Zobrazit plný text záznamu View this record from Arxiv