A hybrid neural network and virtual relality system for spatial language processing

Martinez, G.C., Cangelosi, A and Coventry, K.R. ORCID: https://orcid.org/0000-0003-2591-7723 (2001) A hybrid neural network and virtual relality system for spatial language processing. In: Proceedings of the 2001 International Joint Conference on Neural Networks, Washington DC. The Institute of Electrical and Electronics Engineers (IEEE), pp. 16-21.

Full text not available from this repository. (Request a copy)

Abstract

This paper describes a neural network model for the study of spatial language. It deals with both geometric and functional variables, which have been shown to play an important role in the comprehension of spatial prepositions. The network is integrated with a virtual reality interface for the direct manipulation of geometric and functional factors. The training uses experimental stimuli and data. Results show that the networks reach low training and generalization errors. Cluster analyses of hidden activation show that stimuli primarily group according to extrageometrical variables.

Item Type:	Book Section
Faculty \ School:	Faculty of Social Sciences > School of Social Work and Psychology (former - to 2012) Faculty of Social Sciences > School of Psychology
UEA Research Groups:	Faculty of Social Sciences > Research Groups > Cognition, Action and Perception
Depositing User:	Pure Connector
Date Deposited:	17 May 2016 15:00
Last Modified:	23 Jul 2024 15:31
URI:	https://ueaeprints.uea.ac.uk/id/eprint/58802
DOI:

Actions (login required)

View Item