Home > Research > Publications & Outputs > A Connectionist Model of Spatial Knowledge Acqu...

Electronic data

View graph of relations

A Connectionist Model of Spatial Knowledge Acquisition in a Virtual Environment

Research output: Contribution to conference - Without ISBN/ISSN Conference paperpeer-review

Published
Close
Publication date2003
Number of pages8
Pages40-47
<mark>Original language</mark>English
EventProceedings of International Conference on User Modeling, Workshop on User Modeling, Information Retrieval and Machine Learning. -
Duration: 1/01/1900 → …

Conference

ConferenceProceedings of International Conference on User Modeling, Workshop on User Modeling, Information Retrieval and Machine Learning.
Period1/01/00 → …

Abstract

This paper proposes the use of neural networks as a tool for studying navigation within virtual worlds. Results indicate that network learned to predict the next step for a given trajectory, acquiring also basic spatial knowledge in terms of landmarks and configuration of spatial layout. In addition, the network built a spatial representation of the virtual world, e.g. cognitive-like map, which preserves the topology but lacks metric accuracy. The benefits of this approach and the possibility of extending the methodology to the study of navigation in Human Computer Interaction are discussed.