Brain-Inspired Motion Learning in Recurrent Neural Network With Emotion Modulation | |
Huang, Xiao1,2; Wu, Wei1,2; Qiao, Hong2,3,4; Ji, Yidao5 | |
刊名 | IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS |
2018-12-01 | |
卷号 | 10期号:4页码:1153-1164 |
关键词 | Brain-inspired model emotion motion learning recurrent neural network (RNN) |
ISSN号 | 2379-8920 |
DOI | 10.1109/TCDS.2018.2843563 |
通讯作者 | Qiao, Hong(hong.qiao@ia.ac.cn) |
英文摘要 | Based on basic emotion modulation theory and the neural mechanisms of generating complex motor patterns, we introduce a novel emotion-modulated learning rule to train a recurrent neural network, which enables a complex musculoskeletal arm and a robotic arm to perform goal-directed tasks with high accuracy and learning efficiency. Specifically, inspired by the fact that emotions can modulate the process of learning and decision making through neuromodulatory system, we present a model of emotion generation and modulation to adjust the parameters of learning adaptively, including the reward prediction error, the speed of learning, and the randomness in action selection. Additionally, we use Oja learning rule to adjust the recurrent weights in delayed-reinforcement tasks, which outperforms the Hebbian update rule in terms of stability and accuracy. In the experimental section, we use a musculoskeletal model of the human upper limb and a robotic arm to perform goal-directed tasks through trial-and-reward learning, respectively. The results show that emotion-based methods are able to control the arm with higher accuracy and a faster learning rate. Meanwhile, emotional Oja agent is superior to emotional Hebbian one in term of performance. |
资助项目 | Development of Science and Technology of Guangdong province Special Fund Project[2016B090910001] ; Strategic Priority Research Program of CAS[XDB02080003] ; Beijing Municipal Science and Technology[D16110400140000] ; Beijing Municipal Science and Technology[D161100001416001] ; National Natural Science Foundation of China[61210009] ; National Natural Science Foundation of China[61627808] ; National Natural Science Foundation of China[91648205] ; National Natural Science Foundation of China[51705515] ; National Natural Science Foundation of China[U1713201] ; National Natural Science Foundation of China[61702516] |
WOS关键词 | MODEL ; GENERATION ; COGNITION ; MEMORY ; REORGANIZATION ; ACETYLCHOLINE ; ALGORITHMS ; PLASTICITY ; NEURONS ; SIGNALS |
WOS研究方向 | Computer Science ; Robotics ; Neurosciences & Neurology |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:000452636400029 |
资助机构 | Development of Science and Technology of Guangdong province Special Fund Project ; Strategic Priority Research Program of CAS ; Beijing Municipal Science and Technology ; National Natural Science Foundation of China |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/25679] |
专题 | 中国科学院自动化研究所 |
通讯作者 | Qiao, Hong |
作者单位 | 1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Inst Automat, CAS Ctr Excellence Brain Sci & Intelligence Techn, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 4.Chinese Acad Sci, Cloud Comp Ctr, Beijing 100190, Peoples R China 5.Univ Sci & Technol Beijing, Sch Automat & Elect Engn, Beijing 100083, Peoples R China |
推荐引用方式 GB/T 7714 | Huang, Xiao,Wu, Wei,Qiao, Hong,et al. Brain-Inspired Motion Learning in Recurrent Neural Network With Emotion Modulation[J]. IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS,2018,10(4):1153-1164. |
APA | Huang, Xiao,Wu, Wei,Qiao, Hong,&Ji, Yidao.(2018).Brain-Inspired Motion Learning in Recurrent Neural Network With Emotion Modulation.IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS,10(4),1153-1164. |
MLA | Huang, Xiao,et al."Brain-Inspired Motion Learning in Recurrent Neural Network With Emotion Modulation".IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS 10.4(2018):1153-1164. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论