Robert A. Jacobs

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)
While there exist many techniques for finding the parameters that minimize an error function, only those methods that solely perform local computations are used in connectionist networks. The most popular learning algorithm for connectionist networks is the back-propagation procedure, which can be used to update the weights by the method of steepest(More)
A novel modular connectionist architecture is presented in which the networks composing the architecture compete to learn the training patterns. An outcome of the competition is that di erent networks learn di erent training patterns and, thus, learn to compute di erent functions. The architecture performs task decomposition in the sense that it learns to(More)
This article reviews statistical techniques for combining multiple probability distributions. The framework is that of a decision maker who consults several experts regarding some events. The experts express their opinions in the form of probability distributions. The decision maker must aggregate the experts' distributions into a single distribution that(More)
Human observers localize events in the world by using sensory signals from multiple modalities. We evaluated two theories of spatial localization that predict how visual and auditory information are weighted when these signals specify different locations in space. According to one theory (visual capture), the signal that is typically most reliable dominates(More)
In this paper we present a neural network architecture that discovers a recursive decomposition of its input space. Based on a generalization of the modular architecture of Jacobs, Jordan, Nowlan, and Hinton (1991), the architecture uses competition among networks to recursively split the input space into nested regions and to learn separate associative(More)
This article investigates the bias and variance of mixtures-of-experts (ME) architectures. The variance of an ME architecture can be expressed as the sum of two terms: the first term is related to the variances of the expert networks that comprise the architecture and the second term is related to the expert networks' covariances. One goal of this article(More)
We report the results of a depth-matching experiment in which subjects were asked to adjust the height of an ellipse until it matched the depth of a simulated cylinder defined by texture and motion cues. In one-third of the trials the shape of the cylinder was primarily given by motion information, in another one-third of the trials it was given by texture(More)
We study the hypothesis that observers can use haptic percepts as a standard against which the relative reliabilities of visual cues can be judged, and that these reliabilities determine how observers combine depth information provided by these cues. Using a novel visuo-haptic virtual reality environment, subjects viewed and grasped virtual objects. In(More)