Character recognition by associative completion on words

Author

Tsunoda, Tatsuhiko ; Shiraishi, Tomoyuki ; Tanaka, Hidehiko

Author_Institution

Dept. of Electr. Eng., Tokyo Univ., Japan

Volume

2

fYear

1993

fDate

25-29 Oct. 1993

Firstpage

1135

Abstract

Proposes a new PDAI&CD architecture and applies it to the problem of character recognition. Association is one of the most primitive functions of inference and learning from the dynamically changing outer world. PDAI&CD is just based on such a free-association function and on restrictions for ambiguity resolutions derived from strict knowledge stored as symbolic logic. As an example of PDAI&CD architecture, the system consists of an ART type neural network and of a logical word completion system which uses a spell checker. The experimental results obtained are shown here.

Keywords

ART neural nets; character recognition; inference mechanisms; learning (artificial intelligence); ART type neural network; PDAI&CD architecture; ambiguity resolutions; associative completion; character recognition; free-association function; inference; learning; logical word completion system; spell checker; symbolic logic; Character recognition; Feedforward systems; Humans; Logic; Neural networks; Pattern recognition; Resonance; Shape; Signal resolution; Subspace constraints;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1993. IJCNN '93-Nagoya. Proceedings of 1993 International Joint Conference on

Print_ISBN

0-7803-1421-2

Type

conf

DOI

10.1109/IJCNN.1993.716736

Filename

716736