自动化学报Issue(11)：2428-2435,8.DOI:10.3724/SP.J.1004.2014.02428
一种基于L1范数正则化的回声状态网络
An Improved Echo State Network via L 1-Norm Regularization
摘要
Abstract
Considering the ill-posed problem and the model scale control of echo state network, an improved echo state network based on L1-norm regularization is proposed. In order to improve the numerical stability, the proposed method adds an L1-norm penalty term in the objective function. Meanwhile, the method can also control the complexity of the network and prevent overfitting by using feature selection capability of L1-norm regularization. To solve the L1-norm regularization model, we adopt the least angle regression algorithm to calculate regularization path and select suitable model through Bayesian information criterion, which can avoid the estimations of regularization parameter. The model is applied to the time series predictions of both synthetic dataset and practical dataset. The simulation results show the effectiveness and practicality of the proposed method.关键词
回声状态网络/正则化/最小角回归/信息准则/多元时间序列Key words
Echo state network (ESN)/regularization/least angle regression (LARS)/information criterion/multivariate time series引用本文复制引用
韩敏,任伟杰,许美玲..一种基于L1范数正则化的回声状态网络[J].自动化学报,2014,(11):2428-2435,8.基金项目
国家重点基础研究发展计划(973计划)(2013CB430403),国家自然科学基金(61374154)资助@@@@Supported by National Basic Research Program of China (973 Program)(2013CB430403) and National Natural Science Foun-dation of China (61374154) （973计划）
