Sciweavers

1541 search results - page 44 / 309
» Learning to Diagnose by Doing
Sort
View
ECML
2003
Springer
14 years 1 months ago
Support Vector Machines with Example Dependent Costs
Abstract. Classical learning algorithms from the fields of artificial neural networks and machine learning, typically, do not take any costs into account or allow only costs depe...
Ulf Brefeld, Peter Geibel, Fritz Wysotzki
RA
2003
135views Robotics» more  RA 2003»
13 years 9 months ago
Behavioural Cloning and Robot Control
Behavioural cloning is a method by which a machine learns control skills through observing what a human controller would do in a certain set of circumstances. More specifically, t...
Claire D'Este, Mark O'Sullivan, Nicholas Hannah
NIPS
1996
13 years 9 months ago
Why did TD-Gammon Work?
Although TD-Gammon is one of the major successes in machine learning, it has not led to similar impressive breakthroughs in temporal difference learning for other applications or ...
Jordan B. Pollack, Alan D. Blair
ATAL
2008
Springer
13 years 10 months ago
Using adaptive consultation of experts to improve convergence rates in multiagent learning
In this paper we study the use of experts algorithms in a multiagent setting. In this paper we allow agents to use multiple experts and explore different experts algorithms that a...
Greg Hines, Kate Larson
ECTEL
2007
Springer
14 years 2 months ago
MACE - Enriching Architectural Learning Objects for Experience Multiplication
Education in architecture requires access to a broad range of learning materials to develop flexibility and creativity in design. The learning material is compromised of textual an...
Moritz Stefaner, Elisa Dalla Vecchia, Massimiliano...