一种基于脑网络的分层模块化回声状态网络

doi:10.3901/JME.2015.22.128

机械工程学报

• 汽车非线性动力学及其在复杂机电控制中的应用专栏 • 上一篇下一篇

一种基于脑网络的分层模块化回声状态网络

李丁园^1,2,3, 刘富¹, 乔俊飞^2,3

1. 吉林大学通信工程学院长春 130022；
2. 北京工业大学电子信息与控制工程学院北京 100124；
3. 北京工业大学计算智能与智能系统北京市重点实验室北京 100124

收稿日期:2015-02-28 修回日期:2015-08-23 出版日期:2015-11-15 发布日期:2015-11-15
通讯作者: 乔俊飞，男，1968年出生，博士，教授。主要研究方向为智能控制与智能信息处理。 E-mail：ixibox@sina.com
作者简介:李丁园，女，1987年出生，博士研究生。主要研究方向为智能信息处理及神经网络结构优化设计。 E-mail：dyli@mails.jlu.edu.cn
基金资助:
国家自然科学基金资助项目(61034008，61203099，61225016)

A Hierarchical Modular Echo State Network Based on Brain Networks

LI Dingyuan ^1,2,3, LIU Fu¹, QIAO Junfei ^2,3

1. College of Communication Engineering, Jilin University, Changchun 130022;
2. College of Electronic Information and Control Engineering, Beijing University Technology, Beijing 100124;
3. Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing University Technology, Beijing 100124

Received:2015-02-28 Revised:2015-08-23 Online:2015-11-15 Published:2015-11-15

摘要/Abstract

摘要： 针对回声状态网络(Echo state network, ESN)结构设计问题，提出一种基于脑网络的分层模块化回声状态网络(Hierarchical modular echo state network, HMESN)。脑网络的拓扑结构使功能网络具有丰富的动力学特性，因此，从生物仿生学角度出发，对HMESN的储备池进行分层设计，各层级上的神经元采用小世界网络构建算法生成模块化结构，并引入层级连接。基于脑网络分层模块化的拓扑特征弱化了神经元间的耦合程度，从而使神经元的动力学特性更为丰富，在功能与结构上更接近于真实生物神经网络，有效地提高了网络处理问题的能力。采用Mackey-Glass时间序列预测和非线性系统辨识对网络进行验证，证明该网络的有效性和可行性。

关键词: 储备池, 回声状态网络, 脑网络, 时间序列预测

Abstract: For the structure design of echo state network (ESN), a novel hierarchical modular echo state network (HMESN) based on brain networks is established. The topology of brain networks makes functional networks with rich dynamic behavior. Therefore, from a biological bionic point of view, the reservoir of HMESN for hierarchical design, each level of neurons using small world network construction algorithm to generate modular structure, as well as considered the hierarchical connection .Based on the topological characteristics of hierarchical modular in brain network, it weakens the coupling intensity among neurons, and enriches the dynamics of internal neurons. HMESN’s reservoir is closer to the real biological neural networks from both structural and functional perspectives, which effectively improves the information processing ability of network. Finally, this proposed network is used for the Mackey-Glass time series prediction and the non-linear system identification to prove its validity and feasibility.

Key words: brain networks, echo state network, reservoir, time series prediction

李丁园, 刘富, 乔俊飞. 一种基于脑网络的分层模块化回声状态网络[J]. 机械工程学报, doi: 10.3901/JME.2015.22.128.

LI Dingyuan,LIU Fu, QIAO Junfei . A Hierarchical Modular Echo State Network Based on Brain Networks[J]. Journal of Mechanical Engineering, doi: 10.3901/JME.2015.22.128.

参考文献

[1] JAEGER H. The “echo State” Approach to analyzing and training recurrent neural networks[R]. Berlin：German National Research Center for Information Technology, 2001.
[2] SKOWRONSKI M D, HARRIS J G. Minimum mean squared error time series classification using an echo state network prediction model[C]//Proceedings of the International Symposium on Circuits and Systems. Island of Kos：Circuits and Systems , 2006：3153-3156.
[3] TONG M H, BICKETT A D, CHRISTIANSEN E M, et al. Learning grammatical structure with echo state networks[J]. Neural Network, 2007, 20(3)：424-432.
[4] 乔俊飞, 薄迎春, 韩广. 基于ESN的多指标DHP控制策略在污水处理过程中的应用[J]. 自动化学报, 2013, 39(2)：1146-1151.QIAO Junfei, BO Yingchun, HAN Guang. Application of ESN-based multi indices dual heuristic dynamic programming on wastewater treatment process[J]. Acta Automatic Sinica, 2013, 39(2)：1146-1151.
[5] JAEGER H, HAAS H. Harnessing nonlinearity: Predicting chaotic systems and saving energy in wireless communication[J]. Science, 2004, 304(5667)：78-80.
[6] 韩敏, 穆大芸. 回声状态网络LM算法及混沌时间序列预测[J]. 控制与决策, 2011, 26(10)：1469-1478.HAN Min, MU Dayun. LM algorithm in echo state network for chaotic time series prediction[J]. Control and Decision, 2011, 26(10)：1469-1478.
[7] XUE Y B, YANG L, HAYKIN S. Decoupled echo state networks with lateral inhibition[J]. Neural Networks, 2007, 20(3)：365-376.
[8] RODAN A, TINO P. Minimum complexity echo state network[J]. IEEE Transaction on Neural Networks, 2011, 22(1)：131-144.
[9] SONG Qingsong, FENG Zuren. Effects of connectivity structure of complex echo state network on its prediction performance for nonlinear time series[J]. Neurocomputing, 2010, 73(10-12)：2177-2185.
[10] CUI Hongyan, LIU Xiang, LI Lixiang. The architecture of dynamic reservoir in the echo state network[J]. Chaos, 2012, 22(3)：033127.
[11] MEUNIER D, LAMBIOTTE R, BULLMORE E T. Modular and hierarchically modular organization of brain networks[J]. Frontiers in Neuroscience, 2010, 200：1-11.
[12] KAISER M. A tutorial in connectome analysis: Topological and spatial features of brain networks[J]. NeuroImage, 2011, 57(3)：892-907.
[13] WATTS D J, STROGATZ S H. Collective dynamics of ‘small-world’ networks[J]. Nature, 1998, 393(6684)：440-442.
[14] NEWMAN M E J, WATTS D J. Renormalization group analysis of the small-world network model[J]. Physics Letters A, 1999, 263(4-6)：341-346.
[15] MACKEY M C, GLASS L. Oscillation and chaos in physiological control systems[J]. Science, 1977, 197(4300)：287-289.
[16] HAN Honggui, QIAO Junfei. A self-organizing fuzzy neural network based on a growing-and-pruning algorithm[J]. IEEE Transactions on Neural Network, 2010, 18(6)：1129-1143.

一种基于脑网络的分层模块化回声状态网络

A Hierarchical Modular Echo State Network Based on Brain Networks

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价