| |
Abstract:
A simple but powerful modification of the standard Gaussian
distribution is studied. The variables of the rectified Gaussian
are constrained to be nonnegative, enabling the use of nonconvex
energy functions. Two multimodal examples, the competitive and
cooperative distributions, illustrate the representational power of
the rectified Gaussian. Since the cooperative distribution can
represent the translations of a pattern, it demonstrates the
potential of the rectified Gaussian for modeling pattern manifolds.
The problem of learning may be more tractable for the rectified
Gaussian than for the Boltzmann machine, owing to the technical
advantages of continuous variables.
|
