Learn More
We present a new supervised learning procedure for systems composed of many separate networks, each of which learns to handle a subset of the complete set of training cases. The new procedure can be viewed either as a modular version of a multilayer supervised network, or as an associative version of competitive learning. It therefore provides a new link(More)
The assumption that acquired characteristics are not inherited is often taken to imply that the adaptations that an organism learns during its lifetime cannot guide the course of evolution. This inference is incorrect (Baldwin, 1896). Learning alters the shape of the search space in which evolution operates and thereby provides good evolutionary paths(More)
Rumelhart, Hinton and Williams [Rumelhart et al. 86] describe a learning procedure for layered networks of deterministic, neuron-like units. This paper describes further research on the learning procedure. We start by describing the units, the way they are connected, the learning procedure, and the extension to iterative nets. We then give an example in(More)
We present a new approach to computing from image sequences the two-dimensional velocities of moving objects that are occluded and transparent. The new motion model does not attempt to provide an accurate representation of the velocity flow field at fine resolutions but coarsely segments an image into regions of coherent motion, provides an estimate of(More)
One popular class of unsupervised algorithms are competitive algorithms. In the traditional view of competition, only one competitor, the winner, adapts for any given case. I propose to view competitive adaptation as attempting to fit a blend of simple probability generators (such as gaussians) to a set of data-points. The maximum likelihood fit of a model(More)
ACKNOWLEDGEMENTS The in BLOCKINuence of Andrew Barto and Michael Jordan on my thinking is evidenced throughout this dissertation. They provided technical training, constructive criticism, guidance, and inspiration throughout my tenure as a graduate student. Andy helped me to discriminate between vital research topics and those of secondary import, and urged(More)
A computational model for motion processing in area MT is presented that is based on the observed response properties of cortical neurons and is consistent with the visual perception of partially occluded and transparent moving stimuli. In contrast to models of motion processing that assume spatial continuity and fail to compute the correct velocity for(More)
We describe an extension to the Mixture of Experts architecture for modelling and controlling dynamical systems which exhibit multiple modes of behavior. This extension is based on a Markov process model, and suggests a recurrent network for gating a set of linear or non-linear controllers. The new architecture is demonstrated to be capable of learning(More)
A network model of disparity estimation was developed based on disparity-selective neurons, such as those found in the early stages of processing in the visual cortex. The model accurately estimated multiple disparities in regions, which may be caused by transparency or occlusion. The selective integration of reliable local estimates enabled the network to(More)