点击次数：

论文类型：期刊论文

发表时间：2012-05-01

发表刊物：IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS

收录刊物：SCIE、EI、Scopus

卷号：23

期号：5

页面范围：787-799

ISSN号：2162-237X

关键字：Echo state network (ESN); Laplace likelihood function; robust model; surrogate function

摘要：In this paper, a robust recurrent neural network is presented in a Bayesian framework based on echo state mechanisms. Since the new model is capable of handling outliers in the training data set, it is termed as a robust echo state network (RESN). The RESN inherits the basic idea of ESN learning in a Bayesian framework, but replaces the commonly used Gaussian distribution with a Laplace one, which is more robust to outliers, as the likelihood function of the model output. Moreover, the training of the RESN is facilitated by employing a bound optimization algorithm, based on which, a proper surrogate function is derived and the Laplace likelihood function is approximated by a Gaussian one, while remaining robust to outliers. It leads to an efficient method for estimating model parameters, which can be solved by using a Bayesian evidence procedure in a fully autonomous way. Experimental results show that the proposed method is robust in the presence of outliers and is superior to existing methods.