arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1503.03562cs.NEcs.CVcs.LG
收藏

基于期望反向传播的二值多层神经网络图像分类

Training Binary Multilayer Neural Networks for Image Classification using Expectation Backpropagation

Singapore Management University(新加坡管理大学);Columbia University(哥伦比亚大学);Carnegie Mellon University(卡内基梅隆大学)

Zhiyong Cheng, Daniel Soudry, Zexi Mao, Zhenzhong Lan

摘要:

与实权多层神经网络相比,二进制多层神经网络(BMNN)可以在专用硬件上更有效地实现。BMNN已被证明是有效的二进制分类任务的期望反向传播(EBP)算法在高维文本数据集。在本文中,我们研究的能力,BMNN使用EBP算法对多类图像分类任务。在MNIST上研究了具有多隐层和不同隐层单元数的二进制神经网络的性能。我们还探讨了图像空间滤波器的有效性和BMNN的辍学技术。在MNIST数据集上的实验结果表明,EBP在二进制权值下的测试误差为2.12%,在实权值下的测试误差为1.66%,与标准的BP算法在全连接MNN上的测试误差相当.

英文摘要:

Compared to Multilayer Neural Networks with real weights, Binary Multilayer Neural Networks (BMNNs) can be implemented more efficiently on dedicated hardware. BMNNs have been demonstrated to be effective on binary classification tasks with Expectation BackPropagation (EBP) algorithm on high dimensional text datasets. In this paper, we investigate the capability of BMNNs using the EBP algorithm on multiclass image classification tasks. The performances of binary neural networks with multiple hidden layers and different numbers of hidden units are examined on MNIST. We also explore the effectiveness of image spatial filters and the dropout technique in BMNNs. Experimental results on MNIST dataset show that EBP can obtain 2.12% test error with binary weights and 1.66% test error with real weights, which is comparable to the results of standard BackPropagation algorithm on fully connected MNNs.

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。

↑