Sciweavers

2652 search results - page 313 / 531
» Path Differentials and Applications
Sort
View
199
Voted
CEC
2010
IEEE
15 years 8 months ago
Geometric Nelder-Mead Algorithm for the permutation representation
The Nelder-Mead Algorithm (NMA) is an almost half-century old method for numerical optimization, and it is a close relative of Particle Swarm Optimization (PSO) and Differential Ev...
Alberto Moraglio, Julian Togelius
ICML
2010
IEEE
15 years 8 months ago
Learning Fast Approximations of Sparse Coding
In Sparse Coding (SC), input vectors are reconstructed using a sparse linear combination of basis vectors. SC has become a popular method for extracting features from data. For a ...
Karol Gregor, Yann LeCun
233
Voted
ICML
2010
IEEE
15 years 8 months ago
Continuous-Time Belief Propagation
Many temporal processes can be naturally modeled as a stochastic system that evolves continuously over time. The representation language of continuous-time Bayesian networks allow...
Tal El-Hay, Ido Cohn, Nir Friedman, Raz Kupferman
CEC
2008
IEEE
15 years 7 months ago
Regulation of gene regulation - smooth binding with dynamic affinity affects evolvability
Abstract-- Understanding the evolvability of simple differentiating multicellular systems is a fundamental problem in the biology of genetic regulatory networks and in computationa...
Johannes F. Knabe, Chrystopher L. Nehaniv, Maria J...
207
Voted
CORR
2008
Springer
99views Education» more  CORR 2008»
15 years 7 months ago
When is there a representer theorem? Vector versus matrix regularizers
We consider a general class of regularization methods which learn a vector of parameters on the basis of linear measurements. It is well known that if the regularizer is a nondecr...
Andreas Argyriou, Charles A. Micchelli, Massimilia...