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

页码：375 / 384

页数：10

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
BRINDLEY, GS
[J]. 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

← 1 2 →