CASIA OpenIR  > 类脑智能研究中心
A Spiking Neural Network Based Autonomous Reinforcement Learning Model and Its Application in Decision Making
Guixiang Wang1; Yi Zeng1,2; Bo Xu1,2
2016-11
会议名称BICS 2016: The 8th International Conference on Brain Inspired Cognitive Systems
会议录名称Conferences on the 8th International Conference on Brain-inspired Cognitive System
会议日期2016年11月27-30日
会议地点Beijing, China
摘要

In this paper, we propose an autonomous spiking neural network model for decision making. The model is an expansion of the basal ganglia circuitry with automatic environment perception, which constructs environmental states automatically from image inputs. The work in this paper has the following contributions: (1) In our model, the simplified Hodgkin-Huxley computing model is developed to achieve calculation efficiency closed to the LIF model and is used to obtain and test the ionic level properties in cognition. (2) A spike based motion perception mechanism is proposed to extract key elements for learning process from raw pixels without large amount of training. We apply our model in the “flappy bird” game and it play well after dozens of trainings. The model gets similar learning performance with human at the start of training. Besides, our model simulates cognitive defects when blocking some of sodium or potassium ion channels in the Hodgkin-Huxley model and this is an exploration of cognition deep into ionic level


关键词Spiking Neural Network Hodgkin-huxley Basal Ganglia Motion Perception
学科领域交叉与边缘领域的力学
收录类别CPCI-T
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/12619
专题类脑智能研究中心
通讯作者Yi Zeng
作者单位1.Institute of Automation, Chinese Academy of Science
2.Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences,
推荐引用方式
GB/T 7714
Guixiang Wang,Yi Zeng,Bo Xu. A Spiking Neural Network Based Autonomous Reinforcement Learning Model and Its Application in Decision Making[C],2016.
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
A Spiking Neural Net(1649KB)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
[Guixiang Wang]的文章
[Yi Zeng]的文章
[Bo Xu]的文章
百度学术
百度学术中相似的文章
[Guixiang Wang]的文章
[Yi Zeng]的文章
[Bo Xu]的文章
必应学术
必应学术中相似的文章
[Guixiang Wang]的文章
[Yi Zeng]的文章
[Bo Xu]的文章
相关权益政策
暂无数据
收藏/分享
文件名: A Spiking Neural Network Based Autonomous Reinforcement Learning Model and Its Application in Decision Making.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。