Efficient supervised learning of multilayer feedforward neural networks

Author

Osowski, Stanislaw ; Stodolski, Maciej ; Bojarczak, Piotr

Author_Institution

Inst. of the Theory of Electr. Measure., Tech. Univ. Warsaw, Poland

fYear

1994

fDate

13-16 Apr 1994

Firstpage

393

Abstract

The paper presents the efficient training program of multilayer feedforward neural networks. It is based on the best second order optimization algorithms, including variable metric and conjugate gradient as well as application of directional minimization in each step. The method applies the signal flow graph approach for gradient generation. The results of standard numerical tests are given. The efficiency of the program tested on many examples, including symmetry, parity, dichotomy logistic and 2-spiral problems has shown considerable speed-up over the best, already known reported results

Keywords

feedforward neural nets; interpolation; learning (artificial intelligence); numerical analysis; optimisation; search problems; 2-spiral problems; conjugate gradient; dichotomy logistic; directional minimization; multilayer feedforward neural networks; parity; second order optimization; signal flow graph approach; supervised learning; symmetry; variable metric; Feedforward neural networks; Flow graphs; Logistics; Minimization methods; Multi-layer neural network; Neural networks; Nonhomogeneous media; Signal generators; Supervised learning; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Speech, Image Processing and Neural Networks, 1994. Proceedings, ISSIPNN '94., 1994 International Symposium on

Print_ISBN

0-7803-1865-X

Type

conf

DOI

10.1109/SIPNN.1994.344885

Filename

344885