Solving arithmetic problems using feed-forward neural networks

被引:11
|
作者
Franco, L [1 ]
Cannas, SA [1 ]
机构
[1] Univ Nacl Cordoba, Fac Matemat Astron & Fis, RA-5000 Cordoba, Argentina
关键词
neural networks; arithmetic operations; shifter circuit;
D O I
10.1016/S0925-2312(97)00069-6
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We design new feed-forward multi-layered neural networks which perform different elementary arithmetic operations, such as bit shifting, addition of N p-bit numbers, and multiplication of two n-bit numbers. All the structures are optimal in depth and are polynomially bounded in the number of neurons and in the number of synapses. The whole set of synaptic couplings and thresholds are obtained exactly. (C) 1998 Elsevier Science B.V. All rights reserved.
引用
收藏
页码:61 / 79
页数:19
相关论文
共 50 条