Competition and Multiple Cause Models
- 1 May 1995
- journal article
- Published by MIT Press in Neural Computation
- Vol. 7 (3) , 565-579
- https://doi.org/10.1162/neco.1995.7.3.565
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 (1994a,b). Simulations confirm its efficacy.Keywords
This publication has 5 references indexed in Scilit:
- Learning Factorial Codes by Predictability MinimizationNeural Computation, 1992
- Task Decomposition Through Competition in a Modular Connectionist Architecture: The What and Where Vision TasksCognitive Science, 1991
- Adaptive Mixtures of Local ExpertsNeural Computation, 1991
- Forming sparse representations by local anti-Hebbian learningBiological Cybernetics, 1990
- Finding Minimum Entropy CodesNeural Computation, 1989