HARDWARE REALIZATION OF A NEURON TRANSFER-FUNCTION AND ITS DERIVATIVE

被引：18
|
作者：
ANNEMA, AJ
机构：
[1] MESA Research Institute, University of Twente, 7500A E Enschede
来源：
ELECTRONICS LETTERS | 1994年 / 30卷 / 07期
关键词：
NEURAL NETWORKS;
D O I：
10.1049/el:19940375
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 on-chip learning feedforward neural networks, both a nonlinear sigmoid-like function and its derivative are required. A simple CMOS circuit, based on a CMOS differential pair in weak inversion, that realises both functions is presented.
引用
收藏
页码：576 / 577
页数：2
相关论文
共 50 条
12345