Reinforcement learning algorithm with network extension for pulse neural network

被引:0
|
作者
Takita, M [1 ]
Osana, Y [1 ]
Hagiwara, M [1 ]
机构
[1] Keio Univ, Fac Sci & Technol, Kohoku Ku, Yokohama, Kanagawa 2238522, Japan
关键词
reinforcement learning; pulse neural network;
D O I
暂无
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
In this paper, we propose a new hierarchical pulse neural network and its reinforcement learning algorithm with network extension. The proposed pulse neural network has three layers, and all of the neurons are pulse neurons. This network learns relations between input pulse sequences and the desired outputs by updating connection weights and by adding neurons dynamically. We carried out the computer simulation to confirm the performance of the proposed algorithm.
引用
收藏
页码:2586 / 2591
页数:6
相关论文
共 50 条
  • [31] Prespeech motor learning in a neural network using reinforcement
    Warlaumont, Anne S.
    Westermann, Gert
    Buder, Eugene H.
    Oller, D. Kimbrough
    NEURAL NETWORKS, 2013, 38 : 64 - 75
  • [32] Reinforcement learning with internal expectation for the random neural network
    Halici, U
    EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2000, 126 (02) : 288 - 307
  • [33] Reinforcement learning neural network circuits for electronic nose
    Abdel-Aty-Zohdy, HS
    Al-Nsour, M
    ISCAS '99: PROCEEDINGS OF THE 1999 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOL 5: SYSTEMS, POWER ELECTRONICS, AND NEURAL NETWORKS, 1999, : 379 - 382
  • [34] Applying neural network to reinforcement learning in continuous spaces
    Wang, DL
    Gao, Y
    Yang, P
    ADVANCES IN NEURAL NETWORKS - ISNN 2005, PT 1, PROCEEDINGS, 2005, 3496 : 621 - 626
  • [35] NEURAL NETWORK PRUNING THROUGH CONSTRAINED REINFORCEMENT LEARNING
    Malik, Shehryar
    Haider, Muhammad Umair
    Iqbal, Omer
    Taj, Murtaza
    2022 26TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2022, : 3027 - 3033
  • [36] Recording algorithm for weakly pulse coupled neural network
    Shaaban, KM
    Ali, SA
    Mahdy, YB
    Omar, NM
    PROCEEDING OF THE 2002 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-3, 2002, : 721 - 726
  • [37] Pulse coding off-chip learning algorithm for memristive artificial neural network
    Guo, Ming-Jian
    Duan, Shu-Kai
    Wang, Li-Dan
    CHINESE PHYSICS B, 2022, 31 (07)
  • [38] Extension neural network
    Wang, MH
    Hung, CP
    PROCEEDINGS OF THE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS 2003, VOLS 1-4, 2003, : 399 - 403
  • [39] A novel reinforcement learning algorithm for virtual network embedding
    Yao, Haipeng
    Chen, Xu
    Li, Maozhen
    Zhang, Peiying
    Wang, Luyao
    NEUROCOMPUTING, 2018, 284 : 1 - 9
  • [40] Reinforcement Learning Algorithm for Traffic Steering in Heterogeneous Network
    Adamczyk, Cezary
    Kliks, Adrian
    2021 17TH INTERNATIONAL CONFERENCE ON WIRELESS AND MOBILE COMPUTING, NETWORKING AND COMMUNICATIONS (WIMOB 2021), 2021, : 86 - 89