Search
Now showing items 371-380 of 441
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 ...
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 ...
A Dynamical Systems Model for Language Change
(1995-12-01)
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 ...
Verb Classes and Alternations in Bangla, German, English, and Korean
(1996-05-06)
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 ...
Translation Invariance in Object Recognition, and Its Relation to Other Visual Transformations
(1997-06-01)
Human object recognition is generally considered to tolerate changes of the stimulus position in the visual field. A number of recent studies, however, have cast doubt on the completeness of translation invariance. In a ...
Visual Recognition and Categorization on the Basis of Similarities to Multiple Class Prototypes
(1997-09-01)
To recognize a previously seen object, the visual system must overcome the variability in the object's appearance caused by factors such as illumination and pose. Developments in computer vision suggest that it may be ...
Belief Propagation and Revision in Networks with Loops
(1997-11-01)
Local belief propagation rules of the sort proposed by Pearl(1988) are guaranteed to converge to the optimal beliefs for singly connected networks. Recently, a number of researchers have empirically demonstrated good ...
Properties of Support Vector Machines
(1997-08-01)
Support Vector Machines (SVMs) perform pattern recognition between two point classes by finding a decision surface determined by certain points of the training set, termed Support Vectors (SV). This surface, which in some ...
Visual Segmentation without Classification in a Model of the Primary Visual Cortex
(1997-08-01)
Stimuli outside classical receptive fields significantly influence the neurons' activities in primary visual cortex. We propose that such contextual influences are used to segment regions by detecting the breakdown of ...
Estimating Dependency Structure as a Hidden Variable
(1997-06-01)
This paper introduces a probability model, the mixture of trees that can account for sparse, dynamically changing dependence relationships. We present a family of efficient algorithms that use EMand the Minimum Spanning ...