Sciweavers

2327 search results - page 75 / 466
» Consistency of functional learning methods based on derivati...
Sort
View
IJON
1998
87views more  IJON 1998»
14 years 11 months ago
Learned parametric mixture based ICA algorithm
The learned parametric mixture method is presented for a canonical cost function based ICA model on linear mixture, with several new findings. First, its adaptive algorithm is fu...
Lei Xu, Chi Chiu Cheung, Shun-ichi Amari
ICML
2007
IEEE
16 years 4 days ago
Incremental Bayesian networks for structure prediction
We propose a class of graphical models appropriate for structure prediction problems where the model structure is a function of the output structure. Incremental Sigmoid Belief Ne...
Ivan Titov, James Henderson
ESANN
2001
15 years 21 days ago
Transfer functions: hidden possibilities for better neural networks
Abstract. Sigmoidal or radial transfer functions do not guarantee the best generalization nor fast learning of neural networks. Families of parameterized transfer functions provide...
Wlodzislaw Duch, Norbert Jankowski
SIAMAM
2008
121views more  SIAMAM 2008»
14 years 11 months ago
A Level Set Approach to Anisotropic Surface Evolution with Free Adatoms
We variationally derive a thermodynamically consistent model for surface evolution under the influence of free adatoms. The resulting system of nonlinear partial differential equat...
Christina Stöcker, Axel Voigt
AAAI
2006
15 years 22 days ago
Decision Tree Methods for Finding Reusable MDP Homomorphisms
straction is a useful tool for agents interacting with environments. Good state abstractions are compact, reuseable, and easy to learn from sample data. This paper and extends two...
Alicia P. Wolfe, Andrew G. Barto