Title :
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
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;
Conference_Titel :
Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on
Conference_Location :
Como
Print_ISBN :
0-7695-0619-4
DOI :
10.1109/IJCNN.2000.857881
