Combining dimensions and features in similarity-based representations
| Autor: | Daniel J. Navarro, Michael D. Lee |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
business.industry
PsyArXiv|Social and Behavioral Sciences|Quantitative Methods|Mathematical Psychology bepress|Social and Behavioral Sciences|Psychology|Quantitative Psychology Pattern recognition Bayesian inference Similarity data Data set PsyArXiv|Social and Behavioral Sciences Similarity (psychology) bepress|Social and Behavioral Sciences Selection (linguistics) PsyArXiv|Social and Behavioral Sciences|Quantitative Methods Artificial intelligence business Mathematics |
| Zdroj: | NIPS |
| DOI: | 10.31234/osf.io/qejyb |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|