THE N-N-N CONJECTURE IN ART1

被引:8
作者
GEORGIOPOULOS, M [1 ]
HEILEMAN, GL [1 ]
HUANG, JX [1 ]
机构
[1] UNIV NEW MEXICO,ALBUQUERQUE,NM 87131
关键词
NEURAL NETWORK; PATTERN RECOGNITION; SELF-ORGANIZATION; LEARNING; ADAPTIVE RESONANCE THEORY; ART1;
D O I
10.1016/S0893-6080(05)80135-2
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 consider the ART1 neural network architecture introduced by Carpenter and Grossberg. In their original paper, Carpenter and Grossberg made the following conjecture: In the fast learning case, if the F2 layer in ART1 has at least N nodes, then each member of a list of N input patterns presented cyclically at the F1 layer of ART1 will have direct access to an F2 layer node after at most N list presentations. In this paper, we demonstrate that the conjecture is not valid for certain large L values, where L is a network parameter associated with the adaptation of the bottom-up traces in ART1. It is worth noting that previous work has shown the conjecture to be true for small L values.
引用
收藏
页码:745 / 753
页数:9
相关论文
共 5 条
[1]   A MASSIVELY PARALLEL ARCHITECTURE FOR A SELF-ORGANIZING NEURAL PATTERN-RECOGNITION MACHINE [J].
CARPENTER, GA ;
GROSSBERG, S .
COMPUTER VISION GRAPHICS AND IMAGE PROCESSING, 1987, 37 (01) :54-115
[2]  
CARPENTER GA, 1991, NEURAL NETWORKS F AP
[3]   PROPERTIES OF LEARNING RELATED TO PATTERN DIVERSITY IN ART1 [J].
GEORGIOPOULOS, M ;
HEILEMAN, GL ;
HUANG, J .
NEURAL NETWORKS, 1991, 4 (06) :751-757
[4]  
GROSSBERG S, 1976, BIOL CYBERN, V23, P187
[5]  
MOORE B, 1989, 1988 P CONN MOD SUMM, P174