LOCALLY RECURRENT GLOBALLY FEEDFORWARD NETWORKS - A CRITICAL-REVIEW OF ARCHITECTURES

被引:158
作者
TSOI, AC [1 ]
BACK, AD [1 ]
机构
[1] UNIV NEW S WALES COLL, KENSINGTON, NSW, AUSTRALIA
来源
IEEE TRANSACTIONS ON NEURAL NETWORKS | 1994年 / 5卷 / 02期
基金
澳大利亚研究理事会;
关键词
D O I
10.1109/72.279187
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we will consider a number of local-recurrent-global-feedforward (LRGF) networks that have been introduced by a number of research groups in the past few years. We first analyze the various architectures, with a view to highlighting their differences. Then we introduce a general LRGF network structure that includes most of the network architectures that have been proposed to date. Finally we will indicate some open issues concerning these types of networks.
引用
收藏
页码:229 / 239
页数:11
相关论文
共 66 条
[1]  
ALMEIDA LB, 1987, 1ST P IEEE C NEUR NE, V1, P609
[2]  
ANDERSON B, 1980, OPTIMAL FILTERING
[3]  
[Anonymous], 1980, LINEAR SYSTEMS
[4]  
[Anonymous], 1991, INTRO THEORY NEURAL, DOI DOI 10.1201/9780429499661
[5]  
[Anonymous], 1988, NONLINEAR NONSTATION
[6]   FIR and IIR Synapses, a New Neural Network Architecture for Time Series Modeling [J].
Back, A. D. ;
Tsoi, A. C. .
NEURAL COMPUTATION, 1991, 3 (03) :375-385
[7]  
BACK AD, 1990, P WORKSH NEUR NETW S, P187
[8]  
BACK AD, 1992, ARTIFICIAL NEURAL NE, V2, P1113
[9]  
BACK AD, UNPUB IEEE T NEURAL
[10]  
BACK AD, 1992, P IEEE WORKSHOP, V2, P444