Name
Title | ||
|---|---|---|
Improved Production of Competitive Learning Rules with an Additional Term for Vector Quantization |
Abstract | ||
|---|---|---|
In this work, a general framework for developing learning rules with an added term (perturbation term) is presented. Many learning rules commonly cited in the specialized literature can be derived from this general framework. This framework allows us to introduce some knowledge about vector quantization (as an optimization problem) in the distortion function in order to derive a new learning rule that uses that information to avoid certain local minima of the distortion function, leading to better performance than classical models. Computational experiments in image compression show that our proposed rule, derived from this general framework, can achieve better results than simple competitive learning and other models, with codebooks of less distortion. |
Year | DOI | Venue |
|---|---|---|
2007 | 10.1007/978-3-540-71618-1_51 | ICANNGA (1) |
Keywords | Field | DocType |
added term,improved production,learning rule,better result,competitive learning rules,additional term,general framework,vector quantization,perturbation term,better performance,simple competitive learning,new learning rule,proposed rule,distortion function,competitive learning | Competitive learning,Mathematical optimization,Computer science,Distortion function,Maxima and minima,Vector quantization,Learning rule,Artificial intelligence,Distortion,Optimization problem,Machine learning,Image compression | Conference |
Volume | ISSN | Citations |
4431 | 0302-9743 | 1 |
PageRank | References | Authors |
0.36 | 10 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Enrique Mérida-Casermeiro | 1 | 30 | 5.80 |
| Domingo López-Rodríguez | 2 | 55 | 9.24 |
| Gloria Galán-Marín | 3 | 108 | 9.64 |
| Juan M. Ortiz-De-Lazcano-Lobato | 4 | 13 | 3.00 |