期刊
NEURAL NETWORKS
卷 17, 期 4, 页码 589-609出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.neunet.2004.02.002
关键词
constructive neural networks; network growth; network pruning; training strategy; regression and function approximation
Regression problem is an important application area for neural networks (NNs). Among a large number of existing NN architectures, the feedforward NN (FNN) paradigm is one of the most widely used structures. Although one-hidden-layer feedforward neural networks (OHLFNNs) have simple Structures, they possess interesting representational and learning capabilities. In this paper, we are interested particularly in incremental constructive training of OHL-FNNs. In the proposed incremental Constructive training schemes for an OHL-FNN, input-side training and output-side training may be separated in order to reduce the training time. A new technique is proposed to scale the error signal during the constructive learning process to improve the input-side training efficiency and to obtain better generalization performance. Two pruning methods for removing the input-side redundant connections have also been applied. Numerical simulations demonstrate the potential and advantages of the proposed strategies when compared to other existing techniques in the literature. (C) 2004 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据