Cogent confabulation

被引：35

作者：

Hecht-Nielsen, R ^{[1
]}

机构：

[1] Univ Calif San Diego, Dept Elect & Comp Engn, Inst Neural Computat, La Jolla, CA 92093 USA

来源：

NEURAL NETWORKS | 2005年 / 18卷 / 02期

关键词：

vertebrate cognition; symbolic representations; attractor neural network; cogency; confabulation; duck test; inductive logic; Al;

D O I：

10.1016/j.neunet.2004.11.003

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A new model of vertebrate cognition is introduced: maximization of cogency p(alpha beta gamma delta vertical bar epsilon). This model is shown to be a direct generalization of Aristotelian logic, and to be rigorously related to a calculable quantity. A key aspect of this model is that in Aristotelian logic information environments it functions logically. However, in non-Aristotelian environments, instead of finding the conclusion with the highest probability of being true (a popular past model of cognition); this model instead functions in the manner of the 'duck test;' by finding that conclusion which is most supportive of the truth of the assumed facts. (c) 2004 Elsevier Ltd. All rights reserved.

引用

页码：111 / 115

页数：5

共 7 条

[1]

Amit DJ, 1989, MODELING BRAIN FUNCT, DOI DOI 10.1017/CBO9780511623257

[2] DISTINCTIVE FEATURES, CATEGORICAL PERCEPTION, AND PROBABILITY-LEARNING - SOME APPLICATIONS OF A NEURAL MODEL [J].

ANDERSON, JA ;

SILVERSTEIN, JW ;

RITZ, SA ;

JONES, RS .

PSYCHOLOGICAL REVIEW, 1977, 84 (05) :413-451

[3]

[Anonymous], 2000, CAUSALITY

[4]

Bender E. A., 2000, Mathematical Methods in Artificial Intelligence

[5]

HECHTNIELSEN R, 2004, 0404 U CAL

[6]

Nilsson N J., 1998, Artificial intelligence: a new synthesis

[7] Improved bidirectional retrieval of sparse patterns stored by Hebbian learning [J].

Sommer, FT ;

Palm, G .

NEURAL NETWORKS, 1999, 12 (02) :281-297

← 1 →