Search
Now showing items 1-10 of 24
Sufficient Conditions for Uniform Stability of Regularization Algorithms
(2009-12-01)
In this paper, we study the stability and generalization properties of penalized empirical-risk minimization algorithms. We propose a set of properties of the penalty term that is sufficient to ensure uniform ?-stability: ...
Learning Commonsense Categorical Knowledge in a Thread Memory System
(2004-05-18)
If we are to understand how we can build machines capable of broad purpose learning and reasoning, we must first aim to build systems that can represent, acquire, and reason about the kinds of commonsense knowledge that ...
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 ...
Learning a Color Algorithm from Examples
(1987-06-01)
We show that a color algorithm capable of separating illumination from reflectance in a Mondrian world can be learned from a set of examples. The learned algorithm is equivalent to filtering the image data---in which ...
Learning Physical Descriptions from Functional Definitions, Examples, and Precedents
(1982-11-01)
It is too hard to tell vision systems what things look like. It is easier to talk about purpose and what things are for. Consequently, we want vision systems to use functional descriptions to identify things when ...
Recognition and Structure from One 2D Model View: Observations on Prototypes, Object Classes and Symmetries
(1992-02-01)
In this note we discuss how recognition can be achieved from a single 2D model view exploiting prior knowledge of an object's structure (e.g. symmetry). We prove that for any bilaterally symmetric 3D object one non- ...
Networks and the Best Approximation Property
(1989-10-01)
Networks can be considered as approximation schemes. Multilayer networks of the backpropagation type can approximate arbitrarily well continuous functions (Cybenko, 1989; Funahashi, 1989; Stinchcombe and White, 1989). We ...
Roles of Knowledge in Motor Learning
(1987-02-01)
The goal of this thesis is to apply the computational approach to motor learning, i.e., describe the constraints that enable performance improvement with experience and also the constraints that must be satisfied by ...
Learning object segmentation from video data
(2003-09-08)
This memo describes the initial results of a project to create a self-supervised algorithm for learning object segmentation from video data. Developmental psychology and computational experience have demonstrated that the ...
Iterative Projection Methods for Structured Sparsity Regularization
(2009-10-14)
In this paper we propose a general framework to characterize and solve the optimization problems underlying a large class of sparsity based regularization algorithms. More precisely, we study the minimization of learning ...