Are Neural Fields Suitable for Vector Quantization?

Lucian Alecu 1, 2 Hervé Frezza-Buet 2
1 CORTEX - Neuromimetic intelligence
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : This paper focuses on the possibility of enabling vector quantization learning techniques into dynamic neural fields, as an attempt to enrich their usage in bio-inspired applications. As mathematical approaches prove rather difficult to propose a practical solution, due to the non-linear character of the field equations, we adopt a different perspective in order to deal with this problem. This consists in simulating the evolution of the field and design an empirical method able to measure its quality. The developed benchmark framework implementing this approach is used to check whether a given field is capable to behave as expected in various situations, in particular those involving self-organization by vector quantization.
Document type :
Conference papers
Complete list of metadatas

https://hal-supelec.archives-ouvertes.fr/hal-00351275
Contributor : Sébastien van Luchene <>
Submitted on : Thursday, January 8, 2009 - 7:09:27 PM
Last modification on : Thursday, March 29, 2018 - 11:06:04 AM

Identifiers

Collections

Citation

Lucian Alecu, Hervé Frezza-Buet. Are Neural Fields Suitable for Vector Quantization?. ICMLA'08, Dec 2008, San Diego, United States. pp.239-244, ⟨10.1109/ICMLA.2008.21⟩. ⟨hal-00351275⟩

Share

Metrics

Record views

425