Modular neural networks for solving high complexity problems

被引:2
|
作者
El-Bakry, HM [1 ]
Abo-Elsoud, MA [1 ]
Kamel, MS [1 ]
机构
[1] Mansoura Univ, Fac Comp Sci & Informat Syst, Mansoura, Egypt
来源
ICM 2000: PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE ON MICROELECTRONICS | 2000年
关键词
D O I
10.1109/ICM.2000.916448
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
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 approach is applied to implement XOR functions, 16 logic function 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.
引用
收藏
页码:219 / 222
页数:4
相关论文
共 50 条