Constructive algorithms for structure learning in feedforward neural networks for regression problems

Author

Kwok, Tin-Yau ; Yeung, Dit-Yan

Author_Institution

Dept. of Comput. Sci., Hong Kong Univ. of Sci. & Technol., Kowloon, Hong Kong

Volume

8

Issue

3

fYear

1997

fDate

5/1/1997 12:00:00 AM

Firstpage

630

Lastpage

645

Abstract

In this survey paper, we review the constructive algorithms for structure learning in feedforward neural networks for regression problems. The basic idea is to start with a small network, then add hidden units and weights incrementally until a satisfactory solution is found. By formulating the whole problem as a state-space search, we first describe the general issues in constructive algorithms, with special emphasis on the search strategy. A taxonomy, based on the differences in the state transition mapping, the training algorithm, and the network architecture, is then presented

Keywords

feedforward neural nets; identification; learning (artificial intelligence); neural net architecture; search problems; state-space methods; cascade correlation; constructive algorithms; dynamic nodes; feedforward neural networks; group method of data handling; neural network architecture; projection pursuit regression; resource allocating network; state transition mapping; state-space search; structure learning; Bayesian methods; Data handling; Feedforward neural networks; Heuristic algorithms; Intelligent networks; Network topology; Neural networks; Polynomials; Pursuit algorithms; Taxonomy;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.572102

Filename

572102