Competition and multiple cause models.
Peter Dayan   Rich Zemel
Neural Computation, 7, 565-579.
Abstract
If different causes can interact on any occasion to generate a set of
patterns, then systems modeling the generation have to model the
interaction too. We discuss a way of combining multiple causes that is
based on the integrated segmentation and recognition architecture of
Keeler et al (1991). It is more cooperative than the scheme
embodied in the mixture of experts architecture, which insists that
just one cause generate each output, and more competitive than the
noisy-or combination function, which was recently suggested by
Saund (1994). Simulations confirm its efficacy.
compressed postscript  
pdf