ON SYSTOLIC GENERAL SYSTEM SOLUTION FOR OPTIMAL ARTIFICIAL NEURAL-NETWORK TRAINING

被引:0
|
作者
MARGARITIS, KG
EVANS, DJ
机构
[1] Parallel Algorithms Research Centre, Department of Computer Studies, Loughborough University of Technology
关键词
ARTIFICIAL NEURAL NETWORKS; SYSTOLIC ALGORITHMS AND ARCHITECTURES; GENERAL SYSTEM SOLUTION; GENERALIZED MATRIX INVERSION;
D O I
10.1080/00207169408804336
中图分类号
O29 [应用数学];
学科分类号
070104 ;
摘要
This paper presents systolic algorithms for general system solution and generalised matrix inversion in the context of the optimal linear associative memory artificial neural network, and with applications to optimised training strategies for two layer supervised learning feedforward artificial neural networks.
引用
收藏
页码:33 / 52
页数:20
相关论文
共 50 条