Orthogonal least squares based complex-valued functional link network

详细信息	查看全文 | 推荐本文 |

• 作者：Md. Faijul Amin^a ; ^{amin@synapse.his.u-fukui.ac.jp} ; Ramasamy Savitha^b ; ^{savi0001@e.ntu.edu.sg} ; Muhammad Ilias Amin^c ; ^{ilias.amin@gmail.com} ; Kazuyuki Murase^a ; ^{murase@synapse.his.u-fukui.ac.jp}
• 关键词：Functional link network ; Complex-valued neural network ; Orthogonal least squares ; Function approximation ; Multivariate polynomial
• 刊名：Neural Networks
• 出版年：2012
• 期刊代码：94_08936080
• 类别：cp
• 出版时间：August, 2012
• 卷：32
• 期：Complete
• 页码：257-266
• 文件大小：342 K

摘要

Functional link networks are single-layered neural networks that impose nonlinearity in the input layer using nonlinear functions of the original input variables. In this paper, we present a fully complex-valued functional link network (CFLN) with multivariate polynomials as the nonlinear functions. Unlike multilayer neural networks, the CFLN is free from local minima problem, and it offers very fast learning of parameters because of its linear structure. Polynomial based CFLN does not require an activation function which is a major concern in the complex-valued neural networks. However, it is important to select a smaller subset of polynomial terms (monomials) for faster and better performance since the number of all possible monomials may be quite large. Here, we use the orthogonal least squares (OLS) method in a constructive fashion (starting from lower degree to higher) for the selection of a parsimonious subset of monomials. It is argued here that computing CFLN in purely complex domain is advantageous than in double-dimensional real domain, in terms of number of connection parameters, faster design, and possibly generalization performance. Simulation results on a function approximation, wind prediction with real-world data, and a nonlinear channel equalization problem exhibit that the OLS based CFLN yields very simple structure having favorable performance.