DocumentCode :
424060
Title :
Symbol grounding transfer with hybrid self-organizing/supervised neural networks
Author :
Riga, Thomas ; Cangelosi, Angelo ; Greco, Alberto
Author_Institution :
Adaptive Behavior & Cognition Res. Group, Plymouth Univ., UK
Volume :
4
fYear :
2004
fDate :
25-29 July 2004
Firstpage :
2865
Abstract :
This paper reports new simulations on an extended neural network model for the transfer of symbol grounding. It uses a hybrid and modular connectionist model, consisting of an unsupervised, self-organizing map for stimulus classification and a supervised network for category acquisition and naming. The model is based on a psychologically-plausible view of symbolic communication, where unsupervised concept formation precedes the supervised acquisition of category names. The simulation results demonstrate that grounding is transferred from symbols denoting object properties to newly acquired symbols denoting the object as a whole. The implications for cognitive models integrating neural networks and multi-agent systems are discussed.
Keywords :
category theory; cognitive systems; multi-agent systems; self-organising feature maps; semantic networks; category names; cognitive model; hybrid self-organizing map; multiagent system; semantic interpretation; supervised neural network; symbol grounding transfer; Biological neural networks; Cognition; Cognitive robotics; Computational modeling; Computer networks; Grounding; Neural networks; Psychology; Robot kinematics; Robot sensing systems;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on
ISSN :
1098-7576
Print_ISBN :
0-7803-8359-1
Type :
conf
DOI :
10.1109/IJCNN.2004.1381112
Filename :
1381112
Link To Document :
بازگشت