Reinforcement learning of recurrent neural network for temporal coding

被引：3

作者：

Kimura, Daichi ^{[1
]}

Hayakawa, Yoshinori ^{[1
]}

机构：

[1] Tohoku Univ, Dept Phys, Sendai, Miyagi 9808578, Japan

来源：

NEUROCOMPUTING | 2008年 / 71卷 / 16-18期

关键词：

Temporal coding; Reinforcement learning; Hodgkin-Huxley neuron; Order coding; Phase coding;

D O I：

10.1016/j.neucom.2007.11.014

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We study a reinforcement learning for temporal coding with neural network consisting of stochastic spiking neurons. In neural networks, information can be coded by characteristics of the timing of each neuronal firing, including the order of firing or the relative phase differences of firing. We derive the learning rule for this network and show that the network consisting of Hodgkin-Huxley neurons with the dynamical synaptic kinetics can learn the appropriate timing of each neuronal firing. We also investigate the system size dependence of learning efficiency. (C) 2007 Elsevier B.V. All rights reserved.

引用

页码：3379 / 3386

页数：8

共 50 条

[1] Spiking neural network reinforcement learning method based on temporal coding and STDP
Sboev, Alexander
Vlasov, Danila
Rybka, Roman
Serenko, Alexey
POSTPROCEEDINGS OF THE 9TH ANNUAL INTERNATIONAL CONFERENCE ON BIOLOGICALLY INSPIRED COGNITIVE ARCHITECTURES (BICA 2018), 2018, 145 : 458 - 463
[2] Category learning in a recurrent neural network with reinforcement learning
Zhang, Ying
Pan, Xiaochuan
Wang, Yihong
FRONTIERS IN PSYCHIATRY, 2022, 13
[3] Spiking Neural Network Actor–Critic Reinforcement Learning with Temporal Coding and Reward-Modulated Plasticity
D. S. Vlasov
R. B. Rybka
A. V. Serenko
A. G. Sboev
Moscow University Physics Bulletin, 2024, 79 (Suppl 2) : S944 - S952
[4] Recurrent neural network design for temporal sequence learning
Kwan, HK
Yan, J
PROCEEDINGS OF THE 43RD IEEE MIDWEST SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS I-III, 2000, : 832 - 835
[5] Emergence of Prediction by Reinforcement Learning Using a Recurrent Neural Network
Goto, Kenta
Shibata, Katsunari
JOURNAL OF ROBOTICS, 2010, 2010
[6] A recurrent control neural network for data efficient reinforcement learning
Schaefer, Anton Maximilian
Udluft, Steffen
Zimmermann, Hans-Georg
2007 IEEE INTERNATIONAL SYMPOSIUM ON APPROXIMATE DYNAMIC PROGRAMMING AND REINFORCEMENT LEARNING, 2007, : 151 - +
[7] Temporal difference coding in reinforcement learning
Iwata, K
Ikeda, K
INTELLIGENT DATA ENGINEERING AND AUTOMATED LEARNING, 2003, 2690 : 218 - 227
[8] Training Spiking Neural Networks for Reinforcement Learning Tasks With Temporal Coding Method
Wu, Guanlin
Liang, Dongchen
Luan, Shaotong
Wang, Ji
FRONTIERS IN NEUROSCIENCE, 2022, 16
[9] Learning temporal data with a variational quantum recurrent neural network
Takaki, Yuto
Mitarai, Kosuke
Negoro, Makoto
Fujii, Keisuke
Kitagawa, Masahiro
PHYSICAL REVIEW A, 2021, 103 (05)
[10] Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation
Wang, Lu
Zhang, Wei
He, Xiaofeng
Zha, Hongyuan
KDD'18: PROCEEDINGS OF THE 24TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2018, : 2447 - 2456

← 1 2 3 4 5 →