Trapezoidal Gradient Descent for Effective Reinforcement Learning in Spiking Networks

被引:0
|
作者
Pan, Yuhao [1 ]
Wang, Xiucheng [2 ]
Cheng, Nan [2 ]
Qiu, Qi [1 ]
机构
[1] Xidian Univ, Sch Elect Engn, Xian 710071, Peoples R China
[2] Xidian Univ, Sch Telecommun Engn, Xian 710071, Peoples R China
来源
2024 INTERNATIONAL CONFERENCE ON UBIQUITOUS COMMUNICATION, UCOM 2024 | 2024年
关键词
SNN; reinforcement learning; spike network; trapezoidal function;
D O I
10.1109/UCOM62433.2024.10695930
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
With the rapid development of artificial intelligence technology, the field of reinforcement learning has continuously achieved breakthroughs in both theory and practice. However, traditional reinforcement learning algorithms often entail high energy consumption during interactions with the environment. Spiking Neural Network (SNN), with their low energy consumption characteristics and performance comparable to deep neural networks, have garnered widespread attention. To reduce the energy consumption of practical applications of reinforcement learning, researchers have successively proposed the Pop-SAN and MDC-SAN algorithms. Nonetheless, these algorithms use rectangular functions to approximate the spike network during the training process, resulting in low sensitivity, thus indicating room for improvement in the training effectiveness of SNN. Based on this, we propose a trapezoidal approximation gradient method to replace the spike network, which not only preserves the original stable learning state but also enhances the model's adaptability and response sensitivity under various signal dynamics. Simulation results show that the improved algorithm, using the trapezoidal approximation gradient to replace the spike network, achieves better convergence speed and performance compared to the original algorithm and demonstrates good training stability.
引用
收藏
页码:192 / 196
页数:5
相关论文
共 50 条
  • [41] Learning dynamics of gradient descent optimization in deep neural networks
    Wei WU
    Xiaoyuan JING
    Wencai DU
    Guoliang CHEN
    ScienceChina(InformationSciences), 2021, 64 (05) : 17 - 31
  • [42] Soft-Reward Based Reinforcement Learning by Spiking Neural Networks
    Shi, Weiya
    ADVANCED RESEARCH ON INFORMATION SCIENCE, AUTOMATION AND MATERIAL SYSTEM, PTS 1-6, 2011, 219-220 : 770 - 773
  • [43] Reinforcement Learning in Memristive Spiking Neural Networks through Modulation of ReSuMe
    Ji, Xun
    Zhang, Yaozhong
    Li, Chuxi
    Wu, Tanghong
    Hu, Xiaofang
    ADVANCES IN MATERIALS, MACHINERY, ELECTRONICS III, 2019, 2073
  • [44] Exploring spiking neural networks for deep reinforcement learning in robotic tasks
    Zanatta, Luca
    Barchi, Francesco
    Manoni, Simone
    Tolu, Silvia
    Bartolini, Andrea
    Acquaviva, Andrea
    SCIENTIFIC REPORTS, 2024, 14 (01):
  • [45] MABSearch: The Bandit Way of Learning the Learning Rate-A Harmony Between Reinforcement Learning and Gradient Descent
    Hameed, A. S. Syed Shahul
    Rajagopalan, Narendran
    NATIONAL ACADEMY SCIENCE LETTERS-INDIA, 2024, 47 (01): : 29 - 34
  • [46] BrainQN: Enhancing the Robustness of Deep Reinforcement Learning with Spiking Neural Networks
    Feng, Shuo
    Cao, Jian
    Ou, Zehong
    Chen, Guang
    Zhong, Yi
    Wang, Zilin
    Yan, Juntong
    Chen, Jue
    Wang, Bingsen
    Zou, Chenglong
    Feng, Zebang
    Wang, Yuan
    ADVANCED INTELLIGENT SYSTEMS, 2024, 6 (09)
  • [47] A gradient descent rule for spiking neurons emitting multiple spikes
    Booij, O
    Nguyen, HT
    INFORMATION PROCESSING LETTERS, 2005, 95 (06) : 552 - 558
  • [48] ANALYSIS OF GRADIENT DESCENT LEARNING ALGORITHMS FOR MULTILAYER FEEDFORWARD NEURAL NETWORKS
    GUO, H
    GELFAND, SB
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1991, 38 (08): : 883 - 894
  • [49] Dynamics of on-line gradient descent learning for multilayer neural networks
    Saad, D
    Solla, SA
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 8: PROCEEDINGS OF THE 1995 CONFERENCE, 1996, 8 : 302 - 308
  • [50] The effective noise of stochastic gradient descent
    Mignacco, Francesca
    Urbani, Pierfrancesco
    JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT, 2022, 2022 (08):