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
来源：
SMC 2000 CONFERENCE PROCEEDINGS: 2000 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN & CYBERNETICS, VOL 1-5 | 2000年
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
  • [21] Incremental Learning of Neural Network Classifiers Using Reinforcement Learning
    Bose, Sourabh
    Huber, Manfred
    2016 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC), 2016, : 2097 - 2103
  • [22] Reinforcement Learning and Attractor Neural Network Models of Associative Learning
    Hamid, Oussama H.
    Braun, Jochen
    COMPUTATIONAL INTELLIGENCE, IJCCI 2017, 2019, 829 : 327 - 349
  • [23] Optimizing Artificial Neural Network Learning Using Improved Reinforcement Learning in Artificial Bee Colony Algorithm
    Lamjiak, Taninnuch
    Sirinaovakul, Booncharoen
    Kornthongnimit, Siriwan
    Polvichai, Jumpol
    Sohail, Aysha
    APPLIED COMPUTATIONAL INTELLIGENCE AND SOFT COMPUTING, 2024, 2024
  • [24] Inverted pendulum control of double q-learning reinforcement learning algorithm based on neural network
    Zhang, Daode
    Wang, Xiaolong
    Li, Xuesheng
    Wang, Dong
    UPB Scientific Bulletin, Series D: Mechanical Engineering, 2020, 82 (02): : 15 - 26
  • [25] Accelerating the Deep Reinforcement Learning with Neural Network Compression
    Zhang, Hongjie
    He, Zhuocheng
    Li, Jing
    2019 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2019,
  • [26] A NEURAL NETWORK-LIKE CRITIC FOR REINFORCEMENT LEARNING
    YAMAKAWA, H
    OKABE, Y
    NEURAL NETWORKS, 1995, 8 (03) : 363 - 373
  • [27] Reinforcement learning of recurrent neural network for temporal coding
    Kimura, Daichi
    Hayakawa, Yoshinori
    NEUROCOMPUTING, 2008, 71 (16-18) : 3379 - 3386
  • [28] A Reinforcement Learning Neural Network for Robotic Manipulator Control
    Hu, Yazhou
    Si, Bailu
    NEURAL COMPUTATION, 2018, 30 (07) : 1983 - 2004
  • [29] Investigating the properties of neural network representations in reinforcement learning
    Wang, Han
    Miahi, Erfan
    White, Martha
    Machado, Marlos C.
    Abbas, Zaheer
    Kumaraswamy, Raksha
    Liu, Vincent
    White, Adam
    ARTIFICIAL INTELLIGENCE, 2024, 330
  • [30] Neural Network Approximation for Pessimistic Offline Reinforcement Learning
    Wu, Di
    Jiao, Yuling
    Shen, Li
    Yang, Haizhao
    Lu, Xiliang
    THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 14, 2024, : 15868 - 15877
12345