H.: Are neural fields suitable for vector quantization

This paper focuses on the possibility of enabling vec-tor quantization learning techniques into dynamic neural fields, as an attempt to enrich their usage in bio-inspired applications. As mathematical approaches prove rather dif-ficult to propose a practical solution, due to the non-linear character of the field equations, we adopt a different per-spective in order to deal with this problem. This consists in simulating the evolution of the field and design an em-pirical 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 ex-pected in various situations, in particular those involving self-organization by vector quantization.