Fast Constructive-Covering Algorithm for neural networks and its implement in classification

Di Wang

doi:10.1016/j.asoc.2006.11.011

Fast Constructive-Covering Algorithm for neural networks and its implement in classification

2008-01-01

16

PRE

AI

D

Di Wang *

DOI：10.1016/j.asoc.2006.11.011

原文链接

原文求助

摘要

En 中文

Almost all current training algorithms for neural networks are based on gradient descending technique, which causes long training time. In this paper, we propose a novel fast training algorithm called Fast Constructive-Covering Algorithm (FCCA) for neural network construction based on geometrical expansion. Parameters are updated according to the geometrical location of the training samples in the input space, and each sample in the training set is learned only once. By doing this, FCCA is able to avoid iterative computing and much faster than traditional training algorithms. Given an input sequence in an arbitrary order, FCCA learns easy'' samples first and confusing'' samples are easily learned after these easy'' samples. This sample reordering process is done on the fly based on geometrical concept. In addition, FCCA begins with an empty hidden layer, and adds new hidden neurons when necessary. This constructive learning avoids blind selection of neural network structure. The experimental work for classification problems illustrates the advantages of FCCA, especially in learning speed. (c) 2006 Elsevier B.V. All rights reserved.

Keyword:

neural networks

geometric learning

constructive learning

geometrical expansion

classification

Fast Constructive-Covering Algorithm for neural networks and its implement in classification

摘要

AI总结

期刊

机构

引用论文