Browsing CBCL Memos (1993 - 2004) by Issue Date
Now showing items 1-20 of 123
-
3D Object Recognition: Symmetry and Virtual Views
(1992-12-01)Many 3D objects in the world around us are strongly constrained. For instance, not only cultural artifacts but also many natural objects are bilaterally symmetric. Thoretical arguments suggest and psychophysical ... -
Priors Stabilizers and Basis Functions: From Regularization to Radial, Tensor and Additive Splines
(1993-06-01)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 ... -
Measure Fields for Function Approximation
(1993-06-01)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 ... -
Geometric Structure of the Adaptive Controller of the Human Arm
(1993-07-01)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 ... -
Geometric and Algebraic Aspects of 3D Affine and Projective Structures from Perspective 2D Views
(1993-07-01)We investigate the differences --- conceptually and algorithmically --- between affine and projective frameworks for the tasks of visual recognition and reconstruction from perspective views. It is shown that an affine ... -
Hierarchical Mixtures of Experts and the EM Algorithm
(1993-08-01)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 ... -
On the Convergence of Stochastic Iterative Dynamic Programming Algorithms
(1993-08-01)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 ... -
Conditions for Viewpoint Dependent Face Recognition
(1993-08-01)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 ... -
Example Based Image Analysis and Synthesis
(1993-11-01)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" ... -
Observations on Cortical Mechanisms for Object Recognition andsLearning
(1993-12-01)This paper sketches a hypothetical cortical architecture for visual 3D object recognition based on a recent computational model. The view-centered scheme relies on modules for learning from examples, such as Hyperbf-like ... -
How are Three-Deminsional Objects Represented in the Brain?
(1994-04-01)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 Quadric Reference Surface: Theory and Applications
(1994-06-01)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 ... -
Forecasting Global Temperature Variations by Neural Networks
(1994-08-01)Global temperature variations between 1861 and 1984 are forecast usingsregularization networks, multilayer perceptrons and linearsautoregression. The regularization network, optimized by stochasticsgradient descent associated ... -
Example Based Learning for View-Based Human Face Detection
(1995-01-24)We present an example-based learning approach for locating vertical frontal views of human faces in complex scenes. The technique models the distribution of human face patterns by means of a few view-based "face'' and ... -
Learning from Incomplete Data
(1995-01-24)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 ... -
Fast Object Recognition in Noisy Images Using Simulated Annealing
(1995-01-25)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 ... -
Active Learning with Statistical Models
(1995-03-21)For many types of learners one can compute the statistically 'optimal' way to select data. We review how these techniques have been used with feedforward neural networks. We then show how the same principles may be ... -
Cooperative Physics of Fly Swarms: An Emergent Behavior
(1995-04-11)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 ... -
On Convergence Properties of the EM Algorithm for Gaussian Mixtures
(1995-04-21)"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 ... -
View-Based Strategies for 3D Object Recognition
(1995-04-21)A persistent issue of debate in the area of 3D object recognition concerns the nature of the experientially acquired object models in the primate visual system. One prominent proposal in this regard has expounded the ...
