CASIA OpenIR  > 类脑智能研究中心  > 类脑认知计算
Towards a Brain-inspired Developmental Neural Network by Adaptive Synaptic Pruning
Zhao Feifei1,3; Zhang Tielin1; Zeng Yi1,2,3; Xu Bo1,2,3
2017
会议名称The 24th international Conference on Neural Information Processing (ICONIP 2017)
会议日期November 14-18
会议地点Guangzhou, China, 2017
摘要

It is widely accepted that appropriate network topology should be empirically predefined before training a specific neural network learning task. However, in most cases, these carefully designed networks are easily falling into two kinds of dilemmas: 1) When the data is not enough to train the network well, it will get an underfitting result. 2)When networks have learned too much patterns, they are likely to lead to an overfitting result and have a poor performance on processing new data or transferring to other tasks. Inspired by the synaptic pruning characteristics of the human brain, we propose a brain-inspired developmental neural network (BDNN) algorithm by adaptive synaptic pruning (BDNN-sp) which could get rid of the overfitting and underfitting. The BDNN-sp algorithm adaptively modulates network topology by pruning useless neurons dynamically. In addition, the evolutional optimization method makes the network stop on an appropriate network topology with the best consideration of accuracy and adaptability. Experimental results indicate that the proposed algorithm could automatically find the optimal network topology and the network complexity could adaptively increase along with the increase of task complexity. Compared to the traditional topology-predefined networks, trained BDNN-sp has the similar accuracy but better transfer learning abilities.

关键词Brain-inspired Developmental Neural Network Brain-inspired Pruning Rules Structural Plasticity Network Adaptability Synaptic Pruning
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/23557
专题类脑智能研究中心_类脑认知计算
通讯作者Zeng Yi
作者单位1.Institute of Automation, Chinese Academy of Sciences, Beijing, China
2.Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Shanghai, China
3.University of Chinese Academy of Sciences, Beijing, China
第一作者单位中国科学院自动化研究所
通讯作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Zhao Feifei,Zhang Tielin,Zeng Yi,et al. Towards a Brain-inspired Developmental Neural Network by Adaptive Synaptic Pruning[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
Towards a Brain-insp(387KB)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
[Zhao Feifei]的文章
[Zhang Tielin]的文章
[Zeng Yi]的文章
百度学术
百度学术中相似的文章
[Zhao Feifei]的文章
[Zhang Tielin]的文章
[Zeng Yi]的文章
必应学术
必应学术中相似的文章
[Zhao Feifei]的文章
[Zhang Tielin]的文章
[Zeng Yi]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Towards a Brain-inspired Developmental Neural Network by Adaptive Synaptic Pruning.pdf
格式: Adobe PDF
此文件暂不支持浏览
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。