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

G.C. Martinez; A Cangelosi; K.R. Coventry

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

G.C. Martinez, A Cangelosi, K.R. Coventry

Research output: Chapter in Book/Report/Conference proceeding › Chapter

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.

Original language	English
Title of host publication	Proceedings of the 2001 International Joint Conference on Neural Networks, Washington DC
Publisher	The Institute of Electrical and Electronics Engineers (IEEE)
Pages	16-21
Number of pages	6
Volume	1
Publication status	Published - 2001

Cite this

@inbook{45aadfe740ef4429b48b9241475a78da,

title = "A hybrid neural network and virtual relality system for spatial language processing",

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. Resultsshow that the networks reach low training and generalization errors. Cluster analyses of hidden activation show that stimuli primarily group according to extrageometrical variables.",

author = "G.C. Martinez and A Cangelosi and K.R. Coventry",

year = "2001",

language = "English",

volume = "1",

pages = "16--21",

booktitle = "Proceedings of the 2001 International Joint Conference on Neural Networks, Washington DC",

publisher = "The Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

}

A hybrid neural network and virtual relality system for spatial language processing. / Martinez, G.C.; Cangelosi, A; Coventry, K.R.
Proceedings of the 2001 International Joint Conference on Neural Networks, Washington DC. Vol. 1 The Institute of Electrical and Electronics Engineers (IEEE), 2001. p. 16-21.

Research output: Chapter in Book/Report/Conference proceeding › Chapter

TY - CHAP

T1 - A hybrid neural network and virtual relality system for spatial language processing

AU - Martinez, G.C.

AU - Cangelosi, A

AU - Coventry, K.R.

PY - 2001

Y1 - 2001

N2 - 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. Resultsshow that the networks reach low training and generalization errors. Cluster analyses of hidden activation show that stimuli primarily group according to extrageometrical variables.

AB - 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. Resultsshow that the networks reach low training and generalization errors. Cluster analyses of hidden activation show that stimuli primarily group according to extrageometrical variables.

M3 - Chapter

VL - 1

SP - 16

EP - 21

BT - Proceedings of the 2001 International Joint Conference on Neural Networks, Washington DC

PB - The Institute of Electrical and Electronics Engineers (IEEE)

ER -