Emergent intelligent properties of progressively structured pattern recognition nets

被引：15
作者：
Aleksander, I. [1 ]
机构：
[1] Brunel Univ, Dept Elect Engn & Elect, Uxbridge UB8 3PH, Middx, England
来源：
PATTERN RECOGNITION LETTERS | 1983年 / 1卷 / 5-6期
关键词：
Image recognition; scene analysis;
D O I：
10.1016/0167-8655(83)90075-2
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
The n-tuple recognition net is seen as a building brick of a progression of network structures. The emergent 'intelligent' properties of such systems are discussed. They include the amplification of confidence for the recognition of images that differ in small detail, a short term memory of the last seen image, sequence sensitivity, sequence acceptance and saccadic inspection as an aid in scene analysis.
引用
收藏
页码：375 / 384
页数：10
相关论文
共 12 条
[1]  
Aleksander I., 1982, Digital Systems for Industrial Automation, V1, P305
[2]  
ALEKSANDER I, 1975, Kybernetes, V4, P39, DOI 10.1108/eb005381
[3]  
Aleksander I, 1982, P RANK PRIZ FUND INT
[4]  
Barlow H.B., 1982, P RANK PRIZ FUND INT
[5]  
Boden MA, 1977, ARTIF INTELL
[6]   CLASSIFICATION OF MODIFIABLE SYNAPSES AND THEIR USE IN MODELS FOR CONDITIONING [J].
BRINDLEY, GS .
PROCEEDINGS OF THE ROYAL SOCIETY SERIES B-BIOLOGICAL SCIENCES, 1967, 168 (1013) :361-+
[7]  
Dawson C., 1975, THESIS U KENT CANTER
[8]  
Gregory RL, 1981, MIND SCI
[9]  
McCulloch Warren S., 1943, BULL MATH BIOPHYS, V5, P115, DOI 10.1007/BF02478259
[10]  
Minsky M., 1969, PERCEPTRONS INTRO CO
12