Equivalence between RAM-based neural networks and probabilistic automata

被引：10
作者：
de Souto, MCP
Ludermir, TB
de Oliveira, WR
机构：
[1] Univ Fed Rio Grande do Norte, Dept Informat & Appl Math, BR-59072970 Natal, RN, Brazil
[2] Univ Fed Pernambuco, Ctr Informat, BR-50732970 Recife, PE, Brazil
[3] Rural Fed Univ Pernambuco, Dept Phys & Math, BR-52171900 Recife, PE, Brazil
来源：
IEEE TRANSACTIONS ON NEURAL NETWORKS | 2005年 / 16卷 / 04期
关键词：
automata theory; computability; p random access memory (RAM) node; probabilistic automata; RAM-based neural networks; weightless neural networks (WNNs);
D O I：
10.1109/TNN.2005.849838
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 letter, the computational power of a class of random access memory (RAM)-based neural networks, called general single-layer sequential weightless neural networks (GSSWNNs), is analyzed. The theoretical results presented, besides helping the understanding of the temporal behavior of these networks, could also provide useful insights for the developing of new learning algorithms.
引用
收藏
页码：996 / 999
页数：4
相关论文
共 23 条
[1]  
ADEODATO PJL, P INT C ART NEUR NET, P607
[2]   GENERAL NEURAL UNIT - RETRIEVAL PERFORMANCE [J].
ALEKSANDER, I ;
MORTON, HB .
ELECTRONICS LETTERS, 1991, 27 (19) :1776-1778
[3]  
ALEKSANDER I, 1995, INTRO NEURAL COMPUTI
[4]  
[Anonymous], 1994, P C ADV NEUR INF PRO
[5]  
Browne C, 1996, ELECTRON LETT, V32, P824, DOI 10.1049/el:19960565
[6]  
de Souto M. C. P., 1999, INT J NEURAL SYST, V2, P203
[7]   Encoding of probabilistic automata into RAM-based neural networks [J].
de Souto, MCP ;
Ludermir, TB ;
Campos, MA .
IJCNN 2000: PROCEEDINGS OF THE IEEE-INNS-ENNS INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOL III, 2000, :439-444
[8]  
Fu K. S., 1982, SYNTACTIC PATTERN RE
[9]  
Garcia LAC, 2004, IEEE IJCNN, P2263
[10]   WHAT EVERY COMPUTER SCIENTIST SHOULD KNOW ABOUT FLOATING-POINT ARITHMETIC [J].
GOLDBERG, D .
COMPUTING SURVEYS, 1991, 23 (01) :5-48
123