Sciweavers

394 search results - page 20 / 79
» A Study of Empirical Learning for an Involved Problem
Sort
View
ESWA
2007
100views more  ESWA 2007»
14 years 11 months ago
Treatment of multi-dimensional data to enhance neural network estimators in regression problems
This paper proposes and explains a data treatment technique to improve the accuracy of a neural network estimator in regression problems, where multi-dimensional input data set is...
H. Altun, A. Bilgil, B. C. Fidan
90
Voted
ICML
2008
IEEE
16 years 17 days ago
Active kernel learning
Identifying the appropriate kernel function/matrix for a given dataset is essential to all kernel-based learning techniques. A variety of kernel learning algorithms have been prop...
Steven C. H. Hoi, Rong Jin
NIPS
2008
15 years 1 months ago
Structure Learning in Human Sequential Decision-Making
We use graphical models and structure learning to explore how people learn policies in sequential decision making tasks. Studies of sequential decision-making in humans frequently...
Daniel Acuña, Paul R. Schrater
70
Voted
PRL
2008
93views more  PRL 2008»
14 years 11 months ago
Learning to learn: From smart machines to intelligent machines
Since its birth, more than five decades ago, one of the biggest challenges of artificial intelligence remained the building of intelligent machines. Despite amazing advancements, ...
Bogdan Raducanu, Jordi Vitrià
70
Voted
AAAI
1994
15 years 1 months ago
Dead-End Driven Learning
The paper evaluates the eectiveness of learning for speeding up the solution of constraint satisfaction problems. It extends previous work (Dechter 1990) by introducing a new and ...
Daniel Frost, Rina Dechter