arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1602.07373cs.NEcs.CVcs.LG
收藏

二值化深度神经网络用于图像分类的研究

On Study of the Binarized Deep Neural Network for Image Classification

Fujitsu Research & Development Center(富士通研发中心)

Song Wang, Dongchun Ren, Li Chen, Wei Fan, Jun Sun, Satoshi Naoi

摘要:

近年来,深度神经网络(源于人工神经网络)以其优异的性能引起了众多研究者的关注。然而,由于该网络需要高性能GPU和大存储,因此很难在单个设备上使用它。为了改进深度神经网络,已经通过细化网络结构或训练策略进行了许多尝试。与这些尝试不同,在本文中,我们专注于人工神经网络的基本传播函数,并提出了二值化深度神经网络。该网络是一个纯二进制系统,其中所有的值和计算都是二进制的。因此,我们的网络可以节省大量的计算资源和存储。因此,可以在各种设备上使用它。实验结果证明了该网络的可行性。

英文摘要:

Recently, the deep neural network (derived from the artificial neural network) has attracted many researchers' attention by its outstanding performance. However, since this network requires high-performance GPUs and large storage, it is very hard to use it on individual devices. In order to improve the deep neural network, many trials have been made by refining the network structure or training strategy. Unlike those trials, in this paper, we focused on the basic propagation function of the artificial neural network and proposed the binarized deep neural network. This network is a pure binary system, in which all the values and calculations are binarized. As a result, our network can save a lot of computational resource and storage. Therefore, it is possible to use it on various devices. Moreover, the experimental results proved the feasibility of the proposed network.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑