Structure optimization of neural networks with the A*-algorithm

Author

Doering, Axel ; Galicki, Miroslaw ; Witte, Herbert

Author_Institution

Inst. of Med. Stat., Friedrich-Schiller-Univ., Jena, Germany

Volume

8

Issue

6

fYear

1997

fDate

11/1/1997 12:00:00 AM

Firstpage

1434

Lastpage

1445

Abstract

A method for the construction of optimal structures for feedforward neural networks is introduced. On the basis of a construction of a graph of network structures and an evaluation value which is assigned to each of them, an heuristic search algorithm can be installed on this graph. The application of the A*-algorithm ensures, in theory, both the optimality of the solution and the optimality of the search. For several examples, a comparison between the new strategy and the well-known cascade-correlation procedure is carried out with respect to the performance of the resulting structures

Keywords

feedforward neural nets; graph theory; learning (artificial intelligence); pattern classification; search problems; A*-algorithm; cascade-correlation procedure; feedforward neural networks; heuristic search algorithm; optimality; structure optimization; Art; Computer science education; Electroencephalography; Feedforward neural networks; Heuristic algorithms; Neural networks; Neurons; Optimization methods; Parametric statistics; System identification;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.641466

Filename

641466