Competition and Multiple Cause Models

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.

[1]  Rajesh P. N. Rao,et al.  Dynamic Model of Visual Recognition Predicts Neural Response Properties in the Visual Cortex , 1997, Neural Computation.

[2]  Geoffrey E. Hinton,et al.  Varieties of Helmholtz Machine , 1996, Neural Networks.

[3]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

[4]  Geoffrey E. Hinton,et al.  The Helmholtz Machine , 1995, Neural Computation.

[5]  Eric Saund,et al.  A Multiple Cause Mixture Model for Unsupervised Learning , 1995, Neural Computation.

[6]  R. Zemel A minimum description length framework for unsupervised learning , 1994 .

[7]  Terrence J. Sejnowski,et al.  Grouping Components of Three-Dimensional Moving Objects in Area MST of Visual Cortex , 1994, NIPS.

[8]  Eric Saund,et al.  Unsupervised Learning of Mixtures of Multiple Causes in Binary Data , 1993, NIPS.

[9]  Geoffrey E. Hinton,et al.  Autoencoders, Minimum Description Length and Helmholtz Free Energy , 1993, NIPS.

[10]  Terrence J. Sejnowski,et al.  Filter Selection Model for Generating Visual Motion Signals , 1992, NIPS.

[11]  Jürgen Schmidhuber,et al.  Learning Factorial Codes by Predictability Minimization , 1992, Neural Computation.

[12]  J. Urgen Schmidhuber,et al.  Learning Factorial Codes by Predictability Minimization , 1992 .

[13]  H. Kyburg Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference by Judea Pearl , 1991 .

[14]  Geoffrey E. Hinton,et al.  Adaptive Mixtures of Local Experts , 1991, Neural Computation.

[15]  Michael I. Jordan,et al.  Task Decomposition Through Competition in a Modular Connectionist Architecture: The What and Where Vision Tasks , 1990, Cogn. Sci..

[16]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[17]  James D. Keeler,et al.  Integrated Segmentation and Recognition of Hand-Printed Numerals , 1990, NIPS.

[18]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[19]  H. B. Barlow,et al.  Finding Minimum Entropy Codes , 1989, Neural Computation.

[20]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[21]  L. Baum,et al.  Statistical Inference for Probabilistic Functions of Finite State Markov Chains , 1966 .

[22]  O. L. Zangwill,et al.  Current problems in animal behaviour , 1962 .