基于增量式学习的正则化回声状态网络

针对回声状态网络(ESN)的结构设计问题,提出增量式正则化回声状态网络(IRESN).该网络由相互独立的子储备池模块构成,首先,子储备池根据奇异值分解方法生成,且可以保证每个子储备池权值矩阵的奇异值都小于1;其次,利用问题复杂度或者残差,将网络中逐一添加子储备池,直至满足预设的终止条件,在生成IRESN的过程中,回声状...

Design of incremental regularized echo state network

Aiming at the structure design of an echo state network(ESN), an incremental regularized echo state network(IRESN) is proposed in this paper. The reservoir of the IRESN is composed of independent sub-reservoir modular networks. Firstly, the sub-reservoirs are obtained using the singular value decomposition method, and the singular values of the weight matrix of each sub-reservoir can be guaranteed to be less than one. Then, depending on the problem, complexity or residual error, the sub-reservoirs are added to the network one after another until the preset termination conditions are met. In the process of generating the IRESN, the echo state property can be guaranteed without scaling the reservoir weight matrix. Furthermore, in order to tackle the ill-posed problem, in the process of incremental learning, the output weights are trained using the regularization method, and the leave-one-out cross-validation method is used to select the regularization parameter. The simulation results show that the IRESN has compact structure and high prediction accuracy compared with other ESNs.