| |
Abstract:
The S-Map is a network with a simple learning algorithm that
combines the self-organization capability of the Self-Organizing
Map (SOM) and the probabilistic interpretability of the Generative
Topographic Mapping (GTM). The algorithm is shown to minimize the
same error function as the GTM -- the negative log likelihood --
but when compared to the GTM, the S-Map seems to have a stronger
tendency to self-organize from random initial configuration. The
S-Map algorithm can be further simplified to employ pure Hebbian
learning, without changing the qualitative behaviour of the
network. model.
|
