中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 复杂系统认知与决策实验室
  5. 听觉模型与认知计算
Brain topology improved spiking neural network for efficient reinforcement learning of continuous control

文献类型：期刊论文

作者Wang, Yongjian1,2; Wang, Yansong3,4; Zhang, Xinhe1; Du, Jiulin3,5; Zhang, Tielin1,2,3; Xu, Bo1,2,3,4
刊名FRONTIERS IN NEUROSCIENCE
出版日期2024-04-16
卷号18页码:11
关键词spiking neural network brain topology hierarchical clustering reinforcement learning neuromorphic computing
DOI10.3389/fnins.2024.1325062
通讯作者Du, Jiulin(forestdu@ion.ac.cn) ; Zhang, Tielin(tielin.zhang@ia.ac.cn) ; Xu, Bo(xubo@ia.ac.cn)
英文摘要The brain topology highly reflects the complex cognitive functions of the biological brain after million-years of evolution. Learning from these biological topologies is a smarter and easier way to achieve brain-like intelligence with features of efficiency, robustness, and flexibility. Here we proposed a brain topology-improved spiking neural network (BT-SNN) for efficient reinforcement learning. First, hundreds of biological topologies are generated and selected as subsets of the Allen mouse brain topology with the help of the Tanimoto hierarchical clustering algorithm, which has been widely used in analyzing key features of the brain connectome. Second, a few biological constraints are used to filter out three key topology candidates, including but not limited to the proportion of node functions (e.g., sensation, memory, and motor types) and network sparsity. Third, the network topology is integrated with the hybrid numerical solver-improved leaky-integrated and fire neurons. Fourth, the algorithm is then tuned with an evolutionary algorithm named adaptive random search instead of backpropagation to guide synaptic modifications without affecting raw key features of the topology. Fifth, under the test of four animal-survival-like RL tasks (i.e., dynamic controlling in Mujoco), the BT-SNN can achieve higher scores than not only counterpart SNN using random topology but also some classical ANNs (i.e., long-short-term memory and multi-layer perception). This result indicates that the research effort of incorporating biological topology and evolutionary learning rules has much in store for the future.
WOS关键词CONNECTOME ; MODEL
资助项目Strategic Priority Research Program of Chinese Academy of Sciences[XDA0370305] ; Beijing Nova Program[20230484369] ; Shanghai Municipal Science and Technology Major Project[2021SHZDZX] ; Youth Innovation Promotion Association of Chinese Academy of Sciences
WOS研究方向Neurosciences & Neurology
语种英语
WOS记录号WOS:001258472700001
出版者FRONTIERS MEDIA SA
资助机构Strategic Priority Research Program of Chinese Academy of Sciences ; Beijing Nova Program ; Shanghai Municipal Science and Technology Major Project ; Youth Innovation Promotion Association of Chinese Academy of Sciences
源URL[http://ir.ia.ac.cn/handle/173211/59133]  
专题数字内容技术与服务研究中心_听觉模型与认知计算
通讯作者Du, Jiulin; Zhang, Tielin; Xu, Bo
作者单位1.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China
2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China
3.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, State Key Lab Neurosci, Inst Neurosci, Shanghai, Peoples R China
4.Univ Chinese Acad Sci, Sch Future Technol, Beijing, Peoples R China
5.ShanghaiTech Univ, Sch Life Sci & Technol, Shanghai, Peoples R China
推荐引用方式
GB/T 7714		 Wang, Yongjian,Wang, Yansong,Zhang, Xinhe,et al. Brain topology improved spiking neural network for efficient reinforcement learning of continuous control[J]. FRONTIERS IN NEUROSCIENCE,2024,18:11.
APA Wang, Yongjian,Wang, Yansong,Zhang, Xinhe,Du, Jiulin,Zhang, Tielin,&Xu, Bo.(2024).Brain topology improved spiking neural network for efficient reinforcement learning of continuous control.FRONTIERS IN NEUROSCIENCE,18,11.
MLA Wang, Yongjian,et al."Brain topology improved spiking neural network for efficient reinforcement learning of continuous control".FRONTIERS IN NEUROSCIENCE 18(2024):11.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

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。