计算机技术与发展2017，Vol.27Issue(12)：77-80,4.DOI:10.3969/j.issn.1673-629X.2017.12.017
基于改进激活函数的卷积神经网络研究
Research on Convolutional Neural Network Based on Improved Activation Function
摘要
Abstract
Convolutional neural network is a high degree of abstraction to the human brain and an important part of deep learning. For re-search on it,on the one hand,it is helpful for a more accurate image classification and recognition. On the other hand,the human brain can be more truly simulated,which points out the direction for the development of artificial intelligence. First the advantages and disadvanta-ges of four kinds of activation functions such as Sigmoid,Tanh,ReLu and Softplus are analyzed and compared. Then,combined with the advantages of ReLu and Softplus,a piecewise activation function is designed and constructed. Finally,based on Theano framework and these activation functions,five convolutional neural networks are established respectively for classification recognition on the Cifar-10 da-ta sets. The experimental results show that the convolution neural network based on the improved activation function not only converges faster,but also improves the classification accuracy more effectively.关键词
卷积神经网络/深度学习/人工智能/激活函数Key words
convolutional neural network/deep learning/artificial intelligence/activation function分类
信息技术与安全科学引用本文复制引用
曲之琳,胡晓飞..基于改进激活函数的卷积神经网络研究[J].计算机技术与发展,2017,27(12):77-80,4.基金项目
国家自然科学基金资助项目(61271082) （61271082）
江苏省重点研发计划(BE2015700) （BE2015700）
江苏省自然科学基金(BK20141432) （BK20141432）
