Constructing symbols as manipulable structures by recurrent networks

Author

Taylor, Jg ; Taylor, Nr ; Apolloni, B. ; Orovas, C.

Author_Institution

Dept. of Math., King´´s Coll., London, UK

Volume

2

fYear

2000

fDate

2000

Firstpage

99

Abstract

A simple approach is developed to use semantics as defined by virtual actions to guide the construction of manipulable symbol representations for objects and actions, in particular to obtain a model of syntactic processing in the developing infant. This uses a simplified model of the frontal lobes, and in particular the various sets of neurons involved in the process of chunking of temporal sequences observed in monkeys. The manner in which such neurons play a role in phrase structure grammar is elucidated at a simple level

Keywords

artificial intelligence; grammars; recurrent neural nets; symbol manipulation; temporal reasoning; frontal lobes; manipulable structures; manipulable symbol representations; monkeys; neurons; phrase structure grammar; recurrent networks; semantics; symbol construction; syntactic processing; temporal sequence chunking; Biological neural networks; Brain modeling; Computer science; Educational institutions; Humans; Kirchhoff´s Law; Mathematics; Natural languages; Neural networks; Neurons;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on

Conference_Location

Como

ISSN

1098-7576

Print_ISBN

0-7695-0619-4

Type

conf

DOI

10.1109/IJCNN.2000.857881

Filename

857881