Sciweavers

NIPS
2003
14 years 28 days ago
A Model for Learning the Semantics of Pictures
We propose an approach to learning the semantics of images which allows us to automatically annotate an image with keywords and to retrieve images based on text queries. We do thi...
Victor Lavrenko, R. Manmatha, Jiwoon Jeon
NIPS
2003
14 years 28 days ago
Eigenvoice Speaker Adaptation via Composite Kernel PCA
Eigenvoice speaker adaptation has been shown to be effective when only a small amount of adaptation data is available. At the heart of the method is principal component analysis (...
James T. Kwok, Brian Mak, Simon Ho
NIPS
2003
14 years 28 days ago
Discriminative Fields for Modeling Spatial Dependencies in Natural Images
In this paper we present Discriminative Random Fields (DRF), a discriminative framework for the classification of natural image regions by incorporating neighborhood spatial depe...
Sanjiv Kumar, Martial Hebert
NIPS
2003
14 years 28 days ago
Probabilistic Inference in Human Sensorimotor Processing
When we learn a new motor skill, we have to contend with both the variability inherent in our sensors and the task. The sensory uncertainty can be reduced by using information abo...
Konrad P. Körding, Daniel M. Wolpert
NIPS
2003
14 years 28 days ago
An MCMC-Based Method of Comparing Connectionist Models in Cognitive Science
Despite the popularity of connectionist models in cognitive science, their performance can often be difficult to evaluate. Inspired by the geometric approach to statistical model ...
Woojae Kim, Daniel J. Navarro, Mark A. Pitt, In Ja...
NIPS
2003
14 years 28 days ago
Semi-Supervised Learning with Trees
We describe a nonparametric Bayesian approach to generalizing from few labeled examples, guided by a larger set of unlabeled objects and the assumption of a latent tree-structure ...
Charles Kemp, Thomas L. Griffiths, Sean Stromsten,...
NIPS
2003
14 years 28 days ago
Decoding V1 Neuronal Activity using Particle Filtering with Volterra Kernels
Decoding is a strategy that allows us to assess the amount of information neurons can provide about certain aspects of the visual scene. In this study, we develop a method based o...
Ryan Kelly, Tai Sing Lee
NIPS
2003
14 years 28 days ago
Sparse Representation and Its Applications in Blind Source Separation
In this paper, sparse representation (factorization) of a data matrix is first discussed. An overcomplete basis matrix is estimated by using the K−means method. We have proved ...
Yuanqing Li, Andrzej Cichocki, Shun-ichi Amari, Se...
NIPS
2003
14 years 28 days ago
Subject-Independent Magnetoencephalographic Source Localization by a Multilayer Perceptron
We describe a system that localizes a single dipole to reasonable accuracy from noisy magnetoencephalographic (MEG) measurements in real time. At its core is a multilayer perceptr...
Sung C. Jun, Barak A. Pearlmutter
NIPS
2003
14 years 28 days ago
Algorithms for Interdependent Security Games
Michael J. Kearns, Luis E. Ortiz