CASIA OpenIR  > 类脑智能研究中心
Diverse Neuron Type Selection for Convolutional Neural Networks
Guibo Zhu1; Zhaoxiang Zhang1,2,3; Xu-Yao Zhang1; Cheng-Lin Liu1,2,3
2017
会议名称International Joint Conference on Artificial Intelligence
会议日期August 19-25, 2017
会议地点Australia
摘要
The activation function for neurons is a prominent element in the deep learning architecture for obtaining high performance. Inspired by neuroscience findings, we introduce and define two types of neurons with different activation functions for artificial neural networks: excitatory and inhibitory neurons, which can be adaptively selected by selflearning. Based on the definition of neurons, in the paper we not only unify the mainstream activation functions, but also discuss the complementariness among these types of neurons. In addition, through the cooperation of excitatory and inhibitory neurons, we present a compositional activation function that leads to new state-of-the-art performance comparing to rectifier linear units. Finally, we hope that our framework not only gives a basic unified framework of the existing activation neurons to provide guidance for future design, but also contributes neurobiological explanations which can be treated as a window to bridge the gap between biology and computer science.
收录类别EI
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/20453
专题类脑智能研究中心
通讯作者Zhaoxiang Zhang
作者单位1.Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
3.Center for Excellence in Brain Science and Intelligence Technology, CAS
推荐引用方式
GB/T 7714
Guibo Zhu,Zhaoxiang Zhang,Xu-Yao Zhang,et al. Diverse Neuron Type Selection for Convolutional Neural Networks[C],2017.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
diverse neuron type (259KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Guibo Zhu]的文章
[Zhaoxiang Zhang]的文章
[Xu-Yao Zhang]的文章
百度学术
百度学术中相似的文章
[Guibo Zhu]的文章
[Zhaoxiang Zhang]的文章
[Xu-Yao Zhang]的文章
必应学术
必应学术中相似的文章
[Guibo Zhu]的文章
[Zhaoxiang Zhang]的文章
[Xu-Yao Zhang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: diverse neuron type selection for convolutional neural networks.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。