The notion of generalization ability can be defined precisely as the prediction risk, the expected performance of an estimator in predicting new observations. In this paper, we propose the prediction… (More)

We show that there are strong relationships between approaches to optmization and learning based on statistical physics or mixtures of experts. In particular, the EM algorithm can be interpreted as… (More)

We propose strategies for selecting a good neural network architecture for modeling any spe-ciic data set. Our approach involves eeciently searching the space of possible architectures and selecting… (More)

We apply the Expectation Maximization (EM) algorithm to an assignment problem where in addition to binary assignment variables analog parameters must be estimated. As an example, we use the problem… (More)

Selecting a “best subset” of input variables is a critical issue in forecasting. This is especially true when the number of available input series is large, and exhaustive search through all… (More)

We are interested in the use of analog neural networks for recognizing visual objects. Objects are described by the set of parts they are composed of and their structural relationship. Structural… (More)

I propose a learning algorithm for learning hierarchical models for object recognition. The model architecture is a compositional hierarchy that represents part-whole relationships: parts are… (More)