Modular neural networks for solving high complexity problems

Author

El-Bakry, Hazem M. ; Abo-Elsoud, M.A. ; Kame, M.S.

Author_Institution

Fac. of Comput. Sci. & Inf. Syst., Mansoura Univ., Egypt

fYear

2000

fDate

2000

Firstpage

219

Lastpage

222

Abstract

In this paper, we introduce a powerful solution for complex problems which required to be solved using neural nets. This is done by using modular neural nets (MNNs) that divide the input space into several homogenous regions. Such an approach is applied to implement XOR functions, 16 logic functions on one bit level, and a 2-bit digital multiplier. Compared to previous nonmodular designs, a salient reduction in the order of computations and hardware requirements is obtained

Keywords

computational complexity; logic CAD; logic gates; logic simulation; multiplying circuits; neural nets; problem solving; 1 bit; 2 bit; MNNs; XOR function; complex problems; computations; digital multiplier implementation; hardware requirements; high complexity problem solving; homogenous regions; input space division; logic function implementation; modular neural nets; modular neural networks; neural nets; nonmodular design; Artificial neural networks; Computer architecture; Computer science; Decision making; Information systems; Interference; Logic functions; Multi-layer neural network; Neural networks; Neurons;

fLanguage

English

Publisher

ieee

Conference_Titel

Microelectronics, 2000. ICM 2000. Proceedings of the 12th International Conference on

Conference_Location

Tehran

Print_ISBN

964-360-057-2

Type

conf

DOI

10.1109/ICM.2000.916448

Filename

916448