A connectionist model for category perception: theory and implementation

Author

Basak, Jayanta ; Murthy, C.A. ; Chaudhury, Santanu ; Majumder, Dwijesh Dutta

Author_Institution

Nat. Center for Knowledge Based Comput. Electron., Indian Stat. Inst., Calcutta, India

Volume

4

Issue

2

fYear

1993

fDate

3/1/1993 12:00:00 AM

Firstpage

257

Lastpage

269

Abstract

A connectionist model for learning and recognizing objects (or object classes) is presented. The learning and recognition system uses confidence values for the presence of a feature. The network can recognize multiple objects simultaneously when the corresponding overlapped feature train is presented at the input. An error function is defined, and it is minimized for obtaining the optimal set of object classes. The model is capable of learning each individual object in the supervised mode. The theory of learning is developed based on some probabilistic measures. Experimental results are presented. The model can be applied for the detection of multiple objects occluding each other

Keywords

image recognition; learning (artificial intelligence); neural nets; probability; category perception; connectionist model; error function; image recognition; learning system; overlapped feature train; probability; supervised mode; Abstracts; Artificial intelligence; Biological neural networks; Humans; Multilayer perceptrons; Object detection; Pattern recognition; Problem-solving; Resonance; Supervised learning;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.207613

Filename

207613