Modified Dropout and Maxout based on the MNN for improving accuracy

2020 IEEE 15th International Conference on Solid-State & Integrated Circuit Technology (ICSICT) Pub Date : 2020-11-03 DOI:10.1109/ICSICT49897.2020.9278252

Chao Wang, Xiaojing Zha, Yinshui Xia

引用次数: 1

Abstract

Memristor crossbar array is an emerged architecture suitable for matrix computation. Memristor based neural networks (MNN) address the speed and energy efficiency issues in computing hardware. However, there are still a lot of problems with memristor, and the limited size of memristor crossbar resulting in the accuracy of the MNN is lower than conventional neural networks (CNNs). In this paper, a modified Dropout and Maxout based MNN for improving the accuracy of the MNN is proposed. A three-layer memristor based multilayer Perceptron (MLP) in 64*128 crossbar is built to perform MNIST image recognition. The experiment results demonstrate that the in-situ training of the MLP achieves a high accuracy near 96.5% with Dropout and Maxout.

查看原文本刊更多论文

改进了基于MNN的Dropout和Maxout，提高了精度

忆阻交叉栅阵列是一种新兴的适合于矩阵计算的结构。基于忆阻器的神经网络(MNN)解决了计算硬件中的速度和能效问题。然而，忆阻器仍然存在很多问题，忆阻器横条尺寸的限制导致MNN的精度低于传统的神经网络(cnn)。为了提高MNN的精度，本文提出了一种改进的基于Dropout和Maxout的MNN算法。构建了一种基于三层忆阻器的64*128横条多层感知器(MLP)，用于MNIST图像识别。实验结果表明，基于Dropout和Maxout的MLP原位训练准确率接近96.5%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

2020 IEEE 15th International Conference on Solid-State & Integrated Circuit Technology (ICSICT)

自引率

0.00%

发文量