A model of human knowledge and recognition system based on similarity transformation

Author

Le, Kim

Author_Institution

Sch. of Comput., Canberra Univ., ACT, Australia

fYear

1999

fDate

36495

Firstpage

419

Lastpage

422

Abstract

We propose a model of human knowledge acquisition and recognition process based on a theoretical foundation: similarity transformation. The model is an artificial neural network for pattern recognition (PRANN). Different from conventional ANNs, PRANN has the ability to retrieve individual stored objects, and the recognition process can stop at any sensitivity level at which an abstract image of any abject can be obtained. Based on abstract images, full details of stored images can be recovered approximately

Keywords

knowledge acquisition; neural nets; pattern recognition; PRANN; abstract images; human knowledge acquisition; human knowledge model; individual stored objects; pattern recognition artificial neural network; recognition process; recognition system; sensitivity level; similarity transformation; stored images; theoretical foundation; Artificial neural networks; Australia; Fuzzy sets; Humans; Image recognition; Image retrieval; Information retrieval; Knowledge acquisition; Mathematical model; Pattern recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Knowledge-Based Intelligent Information Engineering Systems, 1999. Third International Conference

Conference_Location

Adelaide, SA

Print_ISBN

0-7803-5578-4

Type

conf

DOI

10.1109/KES.1999.820212

Filename

820212