A cognitive architecture that solves a problem stated by Minsky

Author

Pomi, Andrés ; Mizraji, Eduardo

Author_Institution

Biophys. Dept., Univ. de la Republica, Montevideo, Uruguay

Volume

31

Issue

5

fYear

2001

fDate

10/1/2001 12:00:00 AM

Firstpage

729

Lastpage

734

Abstract

We named “Minsky´s problem” the challenge of building up a cognitive architecture able to perform a good diagnosis based on multiple criteria that arrive one by one as successive clues. This is a remarkable human information processing capability, and a desirable ability for an artificial expert system. We present a general cognitive design that solves Minsky´s problem and a neural network implementation of it that uses distributed associative memories. The type of architecture we present is based on the interaction between an “attribute-object associator (AOA)” and an “intersection filter (IF)” of successive evoked objects, with the intermediation of a working (short-term) memory

Keywords

cognitive systems; content-addressable storage; decision support systems; diagnostic expert systems; neural net architecture; Minsky´s problem; artificial expert system; attribute-object associator; cognitive architecture; diagnosis; distributed associative memories; intersection filter; multiple criteria; neural network; successive clues; successive evoked objects; working memory; Artificial neural networks; Associative memory; Biological neural networks; Books; Computer architecture; Decision making; Diagnostic expert systems; Filters; Humans; Information processing;

fLanguage

English

Journal_Title

Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on

Publisher

ieee

ISSN

1083-4419

Type

jour

DOI

10.1109/3477.956034

Filename

956034