DocumentCode :
2228338
Title :
Modular neural networks for solving high complexity tasks
Author :
El-Bakry, Hazem M. ; Abo-Elsoud, M.A. ; Kamel, M.S.
Author_Institution :
Fac. of Comput. Sci. & Inf. Syst., Mansoura Univ., Egypt
Volume :
3
fYear :
2000
fDate :
2000
Firstpage :
555
Abstract :
In this paper, we introduce a powerful solution for complex problems which are 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 2-bit digital multiplier. Compared to previous non-modular designs, a salient reduction in the order of computations and hardware requirements is obtained
Keywords :
logic gates; multiplying circuits; neural nets; pattern classification; XOR functions; digital multiplier; hardware requirements; high complexity tasks; homogenous regions; input space; logic functions; modular neural networks; nonmodular designs; Artificial neural networks; Computer architecture; Computer science; Information systems; Interference; Logic functions; Multi-layer neural network; Neural networks; Neurons; Power engineering and energy;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Circuits and Systems, 2000. Proceedings. ISCAS 2000 Geneva. The 2000 IEEE International Symposium on
Conference_Location :
Geneva
Print_ISBN :
0-7803-5482-6
Type :
conf
DOI :
10.1109/ISCAS.2000.856120
Filename :
856120
Link To Document :
بازگشت