OPTIMAL UNSUPERVISED LEARNING IN A SINGLE-LAYER LINEAR FEEDFORWARD NEURAL NETWORK

被引：962
作者：
SANGER, TD
机构：
来源：
NEURAL NETWORKS | 1989年 / 2卷 / 06期
关键词：
D O I：
10.1016/0893-6080(89)90044-0
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
引用
收藏
页码：459 / 473
页数：15
相关论文
共 61 条
[1]   RELATIONSHIP BETWEEN SPATIAL-FREQUENCY SELECTIVITY AND RECEPTIVE-FIELD PROFILE OF SIMPLE CELLS [J].
ANDREWS, BW ;
POLLEN, DA .
JOURNAL OF PHYSIOLOGY-LONDON, 1979, 287 (FEB) :163-176
[2]   NEURAL NETWORKS AND PRINCIPAL COMPONENT ANALYSIS - LEARNING FROM EXAMPLES WITHOUT LOCAL MINIMA [J].
BALDI, P ;
HORNIK, K .
NEURAL NETWORKS, 1989, 2 (01) :53-58
[3]  
BALLARD DH, 1987, 6TH P NAT C ART INT, V1, P279
[4]  
BARROW HG, 1987, 1ST P IEEE ANN C NEU, V4, P115
[5]   EARLY VISION AND TEXTURE-PERCEPTION [J].
BERGEN, JR ;
ADELSON, EH .
NATURE, 1988, 333 (6171) :363-364
[6]   THEORY FOR THE DEVELOPMENT OF NEURON SELECTIVITY - ORIENTATION SPECIFICITY AND BINOCULAR INTERACTION IN VISUAL-CORTEX [J].
BIENENSTOCK, EL ;
COOPER, LN ;
MUNRO, PW .
JOURNAL OF NEUROSCIENCE, 1982, 2 (01) :32-48
[7]   AUTO-ASSOCIATION BY MULTILAYER PERCEPTRONS AND SINGULAR VALUE DECOMPOSITION [J].
BOURLARD, H ;
KAMP, Y .
BIOLOGICAL CYBERNETICS, 1988, 59 (4-5) :291-294
[8]   ON AN INCOMPLETELY DETERMINED MODEL FOR FUNCTION APPROXIMATION BY EXPERIMENTAL-DATA [J].
BRAILOVSKY, V .
ANNALS OF THE NEW YORK ACADEMY OF SCIENCES, 1985, 452 :316-333
[9]   ON THE PROBLEM OF FUNCTION SYSTEM SELECTION FOR FUNCTION APPROXIMATION BASED ON THE USE OF A SAMPLE SET WITH DEFECTS [J].
BRAILOVSKY, V .
ANNALS OF THE NEW YORK ACADEMY OF SCIENCES, 1983, 410 (JUL) :149-161
[10]   ON THE PROBLEM OF FUNCTION APPROXIMATION BY SAMPLE SET PROCESSING FOR AN INCOMPLETELY DETERMINED MODEL [J].
BRAILOVSKY, V .
ANNALS OF THE NEW YORK ACADEMY OF SCIENCES, 1983, 410 (JUL) :137-147
1234567