A neocortically-derived model of continuous contextual processing

Author

Garzotto, Andreas ; Aleksandrovsky, Boris ; Lynch, Gary ; Granger, Richard

Author_Institution

Rentenanstalt-Swiss Life, Zurich, Switzerland

Volume

1

fYear

1997

fDate

9-12 Jun 1997

Firstpage

564

Abstract

The architectural regularities shared among most neocortical regions suggest repeated functional units that confer core computational capabilities to otherwise very different cortical areas. This paper addresses the massive cortico-cortical feedforward-feedback system connecting most adjacent cortical areas and discusses a computational model derived from these feedforward-feedback loops. First results obtained using a partial implementation of the model show context-dependent pattern recognition capabilities such as generalization, noise tolerance, pattern completion, and cued associative recall, even with unsegmented input data

Keywords

feedback; feedforward; generalisation (artificial intelligence); neural nets; neurophysiology; pattern recognition; physiological models; context-dependent pattern recognition; continuous contextual processing; core computational capabilities; cortico-cortical feedforward-feedback system; cued associative recall; feedforward-feedback loops; generalization; neocortical regions; neocortically-derived model; noise tolerance; pattern completion; repeated functional units; unsegmented input data; Brain modeling; Computational modeling; Computer science; Context awareness; Context modeling; Detectors; Feedback loop; Feeds; Joining processes; Pattern recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks,1997., International Conference on

Conference_Location

Houston, TX

Print_ISBN

0-7803-4122-8

Type

conf

DOI

10.1109/ICNN.1997.611731

Filename

611731