Improving learning efficiency of recurrent neural network through adjusting weights of all layers in a biologically-inspired framework
Xiao Huang; Wei Wu; Peijie Yin; Hong Qiao
2017
会议名称International Joint Conference on Neural Networks (IJCNN)
会议日期14-19 May 2017
会议地点Anchorage, Alaska
摘要Brain-inspired models have become a focus in artificial intelligence field. As a biologically plausible network, the recurrent neural network in reservoir computing framework has been proposed as a popular model of cortical computation because of its complicated dynamics and highly recurrent connections. To train this network, unlike adjusting only readout weights in liquid computing theory or changing only internal recurrent weights, inspired by global modulation of human emotions on cognition and motion control, we introduce a novel reward-modulated Hebbian learning rule to train the network by adjusting not only the internal recurrent weights but also the input connected weights and readout weights together, with solely delayed, phasic rewards. Experiment results show that the proposed method can train a recurrent neural network in near-chaotic regime to complete the motion control and workingmemory tasks with higher accuracy and learning efficiency.
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/20101
专题复杂系统管理与控制国家重点实验室_机器人理论与应用
推荐引用方式
GB/T 7714
Xiao Huang,Wei Wu,Peijie Yin,et al. Improving learning efficiency of recurrent neural network through adjusting weights of all layers in a biologically-inspired framework[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
Improving learning e(463KB)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
[Xiao Huang]的文章
[Wei Wu]的文章
[Peijie Yin]的文章
百度学术
百度学术中相似的文章
[Xiao Huang]的文章
[Wei Wu]的文章
[Peijie Yin]的文章
必应学术
必应学术中相似的文章
[Xiao Huang]的文章
[Wei Wu]的文章
[Peijie Yin]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Improving learning efficiency of recurrent neural network through adjusting weights of all layers in a biologically-inspired framework.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。