Combining dimensions and features in similarity-based representations
Date
2003
Authors
Navarro, D.
Lee, M.
Editors
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Conference paper
Citation
Advances in neural information processing systems 15: proceedings of the 2002 conference / Suzanna Becker, Sebastian Thrun and Klaus Obermayer (eds.): pp.67-74
Statement of Responsibility
Daniel J. Navarro; Michael D. Lee
Conference Name
Neural Information Processing Systems. Conference (16th : 2002 : British Columbia)
Abstract
This paper develops a new representational model of similarity data that combines continuous dimensions with discrete features. An algorithm capable of learning these representations is described, and a Bayesian model selection approach for choosing the appropriate number of dimensions and features is developed. The approach is demonstrated on a classic data set that considers the similarities between the numbers 0 through 9.