Image analysis and graphics synthesis can be achieved with learning techniques using directly image examples without physically-based, 3D models. In our technique: -- the mapping from novel images to a vector of "pose" ...

Poggio and Vetter (1992) showed that learning one view of a bilaterally symmetric object could be sufficient for its recognition, if this view allows the computation of a symmetric, "virtual," view. Faces are roughly ...

We had previously shown that regularization principles lead to approximation schemes, as Radial Basis Functions, which are equivalent to networks with one layer of hidden units, called Regularization Networks. In this ...

The computation of a piecewise smooth function that approximates a finite set of data points may be decomposed into two decoupled tasks: first, the computation of the locally smooth models, and hence, the segmentation ...

The objects with which the hand interacts with may significantly change the dynamics of the arm. How does the brain adapt control of arm movements to this new dynamic? We show that adaptation is via composition of a ...

We discuss a formulation for active example selection for function learning problems. This formulation is obtained by adapting Fedorov's optimal experiment design to the learning problem. We specifically show how to ...

Global temperature variations between 1861 and 1984 are forecast usingsregularization networks, multilayer perceptrons and linearsautoregression. The regularization network, optimized by stochasticsgradient descent associated ...

The conceptual component of this work is about "reference surfaces'' which are the dual of reference frames often used for shape representation purposes. The theoretical component of this work involves the question ...

We present a tree-structured architecture for supervised learning. The statistical model underlying the architecture is a hierarchical mixture model in which both the mixture coefficients and the mixture components are ...

Recent developments in the area of reinforcement learning have yielded a number of new algorithms for the prediction and control of Markovian environments. These algorithms, including the TD(lambda) algorithm of Sutton ...

We discuss a variety of object recognition experiments in which human subjects were presented with realistically rendered images of computer-generated three-dimensional objects, with tight control over stimulus shape, ...

The processes underlying the perceptual analysis of visual form are believed to have minimal interaction with those subserving the perception of visual motion (Livingstone and Hubel, 1987; Victor and Conte, 1990). ...

Real-world learning tasks often involve high-dimensional data sets with complex patterns of missing features. In this paper we review the problem of learning from incomplete data from two statistical perspectives---the ...

We have simulated the behavior of several artificial flies, interacting visually with each other. Each fly is described by a simple tracking system (Poggio and Reichardt, 1973; Land and Collett, 1974) which summarizes ...

In most classical frameworks for learning from examples, it is assumed that examples are randomly drawn and presented to the learner. In this paper, we consider the possibility of a more active learner who is allowed ...

A fast simulated annealing algorithm is developed for automatic object recognition. The normalized correlation coefficient is used as a measure of the match between a hypothesized object and an image. Templates are ...

Formalizing linguists' intuitions of language change as a dynamical system, we quantify the time course of language change including sudden vs. gradual changes in languages. We apply the computer model to the historical ...

In this report, we investigate the relationship between the semantic and syntactic properties of verbs. Our work is based on the English Verb Classes and Alternations of (Levin, 1993). We explore how these classes are ...

This paper considers the problem of language change. Linguists must explain not only how languages are learned but also how and why they have evolved along certain trajectories and not others. While the language ...

"Expectation-Maximization'' (EM) algorithm and gradient-based approaches for maximum likelihood learning of finite Gaussian mixtures. We show that the EM step in parameter space is obtained from the gradient via a ...