1994 Special Issue: Putative strategies of scene segmentation in monkey visual cortex
Neural Networks - Special issue: models of neurodynamics and behavior
Magnification control in winner relaxing neural gas
Neurocomputing
Self-Organizing Maps for imprecise data
Fuzzy Sets and Systems
| Hi-index | 0.00 |
It is shown that for a class of vector quantization processes, related to neural modeling, that the asymptotic density Q(x ) of the quantization levels in one dimension in terms of the input signal distribution P(x) is a power law Q(x)=C-P(x)α , where the exponent α depends on the number n of neighbors on each side of a unit and is given by α=2/3-1/(3n 2+3[n+1]2). The asymptotic level density is calculated, and Monte Carlo simulations are presented