Sciweavers

715 search results - page 103 / 143
» Neural Network with Matrix Inputs
Sort
View
ICANN
2003
Springer
14 years 1 months ago
Dimension Reduction Based on Orthogonality - A Decorrelation Method in ICA
In independent component analysis problems, when we use a one-unit objective function to iteratively estimate several independent components, the uncorrelatedness between the indep...
Kun Zhang, Lai-Wan Chan
BMCBI
2008
153views more  BMCBI 2008»
13 years 8 months ago
Improved general regression network for protein domain boundary prediction
Background: Protein domains present some of the most useful information that can be used to understand protein structure and functions. Recent research on protein domain boundary ...
Paul D. Yoo, Abdur R. Sikder, Bing Bing Zhou, Albe...
FLAIRS
2007
13 years 11 months ago
Context-Sensitive MTL Networks for Machine Lifelong Learning
Context-sensitive Multiple Task Learning, or csMTL, is presented as a method of inductive transfer that uses a single output neural network and additional contextual inputs for le...
Daniel L. Silver, Ryan Poirier
ICANN
2003
Springer
14 years 1 months ago
Sparse Coding with Invariance Constraints
We suggest a new approach to optimize the learning of sparse features under the constraints of explicit transformation symmetries imposed on the set of feature vectors. Given a set...
Heiko Wersing, Julian Eggert, Edgar Körner
ESANN
2006
13 years 10 months ago
Recognition of handwritten digits using sparse codes generated by local feature extraction methods
We investigate when sparse coding of sensory inputs can improve performance in a classification task. For this purpose, we use a standard data set, the MNIST database of handwritte...
Rebecca Steinert, Martin Rehn, Anders Lansner