首页|基于强化学习的储层神经元筛选优化方法

基于强化学习的储层神经元筛选优化方法

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
随机生成的回声状态网络动态储层存在大量冗余神经元,导致网络高维状态空间矩阵产生共线性问题而影响网络预测性能.为解决该问题,提出一种基于强化学习的储层神经元筛选优化方法(SC-ESN),其实质是基于集成学习的思想构建多个初始储备池,利用互信息度量储层池中每个神经元对网络性能的贡献,并结合强化学习的决策机制筛选出对网络输出有效的神经元,进而达到优化网络结构、提高网络预测性能的目的.基于人工数据集和实际数据集的实验表明,所提出的SC-ESN模型与其他预测模型相比,该模型在保证预测性能的前提下具有最小结构.
Optimization method for reservoir neuron selection based on reinforcement learning
The dynamic reservoir of the randomly generated echo state network(ESN)contains a significant amount of redundant neurons,which leads to collinearity in the high-dimensional state space matrix of the network and subsequently affects its prediction performance.In order to address this issue,this paper proposes a self-organizing choice ESN(SC-ESN)structure optimization model based on reinforcement learning.The essence of the SC-ESN model lies in its construction of multiple initial reserve pools,which is founded upon the idea of ensemble learning.The contribution of each neuron in the reservoir pool to the network performance is then measured using mutual information,and the decision mechanism of reinforcement learning is utilized to screen out effective neurons for network output.The purpose of this optimization is to improve the network's structure and prediction performance.Results of experiments conducted on both manual and actual datasets show that the SC-ESN model proposed has a more streamlined structure while still maintaining superior prediction performance compared to other prediction models.

echo state networkmutual informationreinforcement learningensemble learningstructure optimization

郭伟、姚欢、张昭昭、朱应钦

展开 >

西安科技大学通信与信息工程学院,西安 710054

西安科技大学计算机科学与技术学院,西安 710054

墨西哥国立理工学院高级研究中心控制科学与工程系,墨西哥07360

回声状态网络 互信息 强化学习 集成学习 结构优化

陕西省自然科学基础研究计划陕煤联合基金项目陕西省自然科学基础研究计划项目陕西省自然科学基础研究计划项目国家重点研发计划项目国家重点研发计划项目

2019JLZ-082020JM-5222021JM-3962018YFC1900800-52018YFC1900801

2024

10.13195/j.kzyjc.2023.0444

控制与决策
东北大学

控制与决策

CSTPCD北大核心
影响因子：1.227
ISSN：1001-0920
年,卷(期)：2024.39(9)
  • 5