Sciweavers

986 search results - page 106 / 198
» Zero-data Learning of New Tasks
Sort
View
ICML
2006
IEEE
15 years 10 months ago
A DC-programming algorithm for kernel selection
We address the problem of learning a kernel for a given supervised learning task. Our approach consists in searching within the convex hull of a prescribed set of basic kernels fo...
Andreas Argyriou, Raphael Hauser, Charles A. Micch...
HICSS
2006
IEEE
163views Biometrics» more  HICSS 2006»
15 years 4 months ago
Learning Ranking vs. Modeling Relevance
The classical (ad hoc) document retrieval problem has been traditionally approached through ranking according to heuristically developed functions (such as tf.idf or bm25) or gene...
Dmitri Roussinov, Weiguo Fan
GECCO
2004
Springer
155views Optimization» more  GECCO 2004»
15 years 3 months ago
Genetic Network Programming with Reinforcement Learning and Its Performance Evaluation
A new graph-based evolutionary algorithm named “Genetic Network Programming, GNP” has been proposed. GNP represents its solutions as directed graph structures, which can improv...
Shingo Mabu, Kotaro Hirasawa, Jinglu Hu
CVPR
2008
IEEE
15 years 12 months ago
Looking around the backyard helps to recognize faces and digits
Human beings have the ability to learn to recognize a new visual category based on only one or few training examples. Part of this ability might come from the use of knowledge fro...
Honghao Shan, Garrison W. Cottrell
ICML
2008
IEEE
15 years 10 months ago
Training restricted Boltzmann machines using approximations to the likelihood gradient
A new algorithm for training Restricted Boltzmann Machines is introduced. The algorithm, named Persistent Contrastive Divergence, is different from the standard Contrastive Diverg...
Tijmen Tieleman