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 between these two apparently different a...

A useful strategy to deal with complex classification scenarios is the “divide and conquer” approach. The mixture of experts (MOE) technique makes use of this strategy by joinly training a set of classifiers, or experts, that are specialized in different regions of the input space. A global model, or gate function, complements the experts by learning a function that weights their relevance in d...

The design of future air traffic management (ATM) systems appears as a grand challenge. Because of its very large scale, complexity, and dynamicity, we believe that the future of air traffic management lies in hybrid distributed cooperative control systems, including human experts (air traffic controllers) and also intelligent computer support through artificial agents. Such artificial agents c...

This paper proposes a divide-and-conquer strategy for designing brain machine interfaces. A nonlinear combination of competitively trained local linear models (experts) is used to identify the mapping from neuronal activity in cortical areas associated with arm movement to the hand position of a primate. The proposed architecture and the training algorithm are described in detail and numerical ...

The Mixture of Experts, as it was originally formulated, is a static algorithm in the sense that the output of the network, and parameter updates during training, are completely independent from one time step to the next. This independence creates difficulties when the model is applied to time series prediction. We address this by adding memory to the Mixture of Experts. A Gaussian assumption o...

Genuine partnership between patient groups and medical experts is important but challenging. Our training program meets this challenge by organizing hands-on, lab-based training sessions for members of patient groups. These sessions allow "trainees" to better understand their disease and the biomedical research process, and strengthen links between patients and local researchers. Over the past ...