当前位置: X-MOL 学术EURASIP J. Wirel. Commun. Netw. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Design of a reservoir for cloud-enabled echo state network with high clustering coefficient
EURASIP Journal on Wireless Communications and Networking ( IF 2.6 ) Pub Date : 2020-03-13 , DOI: 10.1186/s13638-020-01672-x
Abbas Akrami , Habib Rostami , Mohammad R. Khosravi

Reservoir computing (RC) is considered as a suitable alternative for descending gradient methods in recursive neural networks (RNNs) training. The echo state network (ESN) is a platform for RC and nonlinear system simulation in the cloud environment with many external users. In the past researches, the highest eigenvalue of reservoir connection weight (spectral radius) was used to predict reservoir dynamics. Some researchers have illustrated; the characteristics of scale-free and small-world can improve the approximation capability in echo state networks; however, recent studies have shown importance of the infrastructures such as clusters and the stability criteria of these reservoirs as altered. In this research, we suggest a high clustered ESN called HCESN that its internal neurons are interconnected in form of clusters. Each of the clusters contains one backbone and a number of local nodes. We implemented a classical clustering algorithm, called K-means, and three optimization algorithms including genetic algorithm (GA), differential evolution (DE), and particle swarm optimization (PSO) to improve the clustering efficiency of the new reservoir and compared them with each other. For investigating the spectral radius and predictive power of the resulting reservoirs, we also applied them to the laser time series and the Mackey-Glass dynamical system. It is demonstrated that new clustered reservoirs have some specifications of biologic neural systems and complex networks like average short path length, high clustering coefficient, and power-law distribution. The empirical results illustrated that the ESN based on PSO could strikingly enhance echo state property (ESP) and obtains less chaotic time series prediction error compared with other works and the original version of ESN. Therefore, it can approximate nonlinear dynamical systems and predict the chaotic time series.



中文翻译:

具有高聚类系数的基于云的回波状态网络储层的设计

在递归神经网络(RNN)训练中,水库计算(RC)被认为是降梯度方法的合适替代方法。回声状态网络(ESN)是一个在云环境中具有许多外部用户的RC和非线性系统仿真的平台。在过去的研究中,储层连接权重的最大特征值(谱半径)被用来预测储层动力学。一些研究人员已经说明了;无标度和小世界的特性可以提高回波状态网络的逼近能力。但是,最近的研究表明,诸如集群之类的基础设施的重要性以及这些水库的稳定性标准已经改变。在这项研究中,我们建议使用称为HCESN的高簇ESN,其内部神经元以簇的形式相互连接。每个群集包含一个主干和多个本地节点。我们实施了一种称为K-means的经典聚类算法,并采用了三种优化算法,包括遗传算法(GA),差分进化(DE)和粒子群优化(PSO),以提高新油藏的聚类效率,并将它们与每种储油库进行比较。其他。为了研究所得储层的光谱半径和预测能力,我们还将其应用于激光时间序列和Mackey-Glass动力学系统。结果表明,新的聚类储集层具有某些生物神经系统和复杂网络的规格,例如平均短程长度,高聚类系数和幂律分布。实验结果表明,与其他工作和原始版本的ESN相比,基于PSO的ESN可以显着增强回波状态特性(ESP),并获得较少的混沌时间序列预测误差。因此,它可以近似非线性动力学系统并预测混沌时间序列。

更新日期:2020-04-21
down
wechat
bug