Sciweavers

2316 search results - page 309 / 464
» The many forms of hypercomputation
Sort
View
ML
2002
ACM
163views Machine Learning» more  ML 2002»
15 years 4 months ago
Structural Modelling with Sparse Kernels
A widely acknowledged drawback of many statistical modelling techniques, commonly used in machine learning, is that the resulting model is extremely difficult to interpret. A numb...
Steve R. Gunn, Jaz S. Kandola
NAR
2002
132views more  NAR 2002»
15 years 4 months ago
euGenes: a eukaryote genome information system
euGenes is a genome information system and database that provides a common summary of eukaryote genes and genomes, at web site http://iubio.bio.indiana.edu/eugenes/. Seven popular...
Donald G. Gilbert
145
Voted
NC
2002
196views Neural Networks» more  NC 2002»
15 years 4 months ago
Beyond second-order statistics for learning: A pairwise interaction model for entropy estimation
Second order statistics have formed the basis of learning and adaptation due to its appeal and analytical simplicity. On the other hand, in many realistic engineering problems requ...
Deniz Erdogmus, José Carlos Príncipe...
PAMI
2002
98views more  PAMI 2002»
15 years 4 months ago
Extraction of Visual Features for Lipreading
The multimodal nature of speech is often ignored in human-computer interaction, but lip deformations and other body motion, such as those of the head, convey additional information...
Iain Matthews, Timothy F. Cootes, J. Andrew Bangha...
TASLP
2002
84views more  TASLP 2002»
15 years 4 months ago
Maximum likelihood multiple subspace projections for hidden Markov models
The first stage in many pattern recognition tasks is to generate a good set of features from the observed data. Usually, only a single feature space is used. However, in some compl...
Mark J. F. Gales