Sciweavers

NIPS
1998
13 years 5 months ago
Divisive Normalization, Line Attractor Networks and Ideal Observers
Gain control by divisive inhibition, a.k.a. divisive normalization, has been proposed to be a general mechanism throughout the visual cortex. We explore in this study the statisti...
Sophie Deneve, Alexandre Pouget, Peter E. Latham
NIPS
1998
13 years 5 months ago
Example-Based Image Synthesis of Articulated Figures
We present a method for learning complex appearance mappings, such as occur with images of articulated objects. Traditional interpolation networks fail on this case since appearan...
Trevor Darrell
NIPS
1998
13 years 5 months ago
Facial Memory Is Kernel Density Estimation (Almost)
We compare the ability of three exemplar-based memory models, each using three different face stimulus representations, to account for the probability a human subject responded &q...
Matthew N. Dailey, Garrison W. Cottrell, Thomas A....
NIPS
1998
13 years 5 months ago
Dynamically Adapting Kernels in Support Vector Machines
The kernel-parameter is one of the few tunable parameters in Support Vector machines, controlling the complexity of the resulting hypothesis. Its choice amounts to model selection...
Nello Cristianini, Colin Campbell, John Shawe-Tayl...
NIPS
1998
13 years 5 months ago
A Phase Space Approach to Minimax Entropy Learning and the Minutemax Approximations
There has been much recent work on measuring image statistics and on learning probability distributions on images. We observe that the mapping from images to statistics is many-to...
James M. Coughlan, Alan L. Yuille
NIPS
1998
13 years 5 months ago
Fisher Scoring and a Mixture of Modes Approach for Approximate Inference and Learning in Nonlinear State Space Models
We present Monte-Carlo generalized EM equations for learning in nonlinear state space models. The dif
Thomas Briegel, Volker Tresp
NIPS
1998
13 years 5 months ago
An Entropic Estimator for Structure Discovery
We introduce a novel framework for simultaneous structure and parameter learning in hidden-variable conditional probability models, based on an entropic prior and a solution for i...
Matthew Brand
NIPS
1998
13 years 5 months ago
Approximate Learning of Dynamic Models
Inference is a key component in learning probabilistic models from partially observable data. When learning temporal models, each of the many inference phases requires a complete ...
Xavier Boyen, Daphne Koller
NIPS
1998
13 years 5 months ago
Lazy Learning Meets the Recursive Least Squares Algorithm
Lazy learning is a memory-based technique that, once a query is received, extracts a prediction interpolating locally the neighboring examples of the query which are considered re...
Mauro Birattari, Gianluca Bontempi, Hugues Bersini