Sciweavers

295 search results - page 24 / 59
» Statistical Methods for Construction of Neural Networks
Sort
View
NN
2000
Springer
177views Neural Networks» more  NN 2000»
13 years 8 months ago
Independent component analysis: algorithms and applications
A fundamental problem in neural network research, as well as in many other disciplines, is finding a suitable representation of multivariate data, i.e. random vectors. For reasons...
Aapo Hyvärinen, Erkki Oja
NIPS
2001
13 years 10 months ago
(Not) Bounding the True Error
We present a new approach to bounding the true error rate of a continuous valued classifier based upon PAC-Bayes bounds. The method first constructs a distribution over classifier...
John Langford, Rich Caruana
GECCO
2010
Springer
191views Optimization» more  GECCO 2010»
14 years 1 months ago
Initialization parameter sweep in ATHENA: optimizing neural networks for detecting gene-gene interactions in the presence of sma
Recent advances in genotyping technology have led to the generation of an enormous quantity of genetic data. Traditional methods of statistical analysis have proved insufficient i...
Emily Rose Holzinger, Carrie C. Buchanan, Scott M....
ICRA
1998
IEEE
105views Robotics» more  ICRA 1998»
14 years 26 days ago
PSOM Network: Learning with Few Examples
: Precise sensorimotor mappings between various motor, ensor, and abstract physical spaces are the basis for many robotics tasks. Their cheap construction is a challenge for adapti...
Jörg A. Walter
ICANN
1997
Springer
14 years 5 days ago
Local Subspace Classifier
Subsystems for on-line recognition of handwriting are needed in personal digital assistants (PDAs) and other portable handheld devices. We have developed a recognition system whic...
Jorma Laaksonen