Sciweavers

1191 search results - page 111 / 239
» Completeness and Performance Of The APO Algorithm
Sort
View
ICML
2008
IEEE
16 years 4 months ago
Learning for control from multiple demonstrations
We consider the problem of learning to follow a desired trajectory when given a small number of demonstrations from a sub-optimal expert. We present an algorithm that (i) extracts...
Adam Coates, Pieter Abbeel, Andrew Y. Ng
147
Voted
ICASSP
2008
IEEE
15 years 10 months ago
Blind audiovisual separation based on redundant representations
In this work we present a method to perform a complete audiovisual source separation without need of previous information. This method is based on the assumption that sounds are c...
Anna Llagostera Casanovas, Gianluca Monaci, Pierre...
142
Voted
IPPS
2002
IEEE
15 years 8 months ago
Static Mapping Heuristics for Tasks with Dependencies, Priorities, Deadlines, and Multiple Versions in Heterogeneous Environment
Heterogeneous computing (HC) environments composed of interconnected machines with varied computational capabilities are well suited to meet the computational demands of large, di...
Tracy D. Braun, Howard Jay Siegel, Anthony A. Maci...
146
Voted
ICDM
2007
IEEE
151views Data Mining» more  ICDM 2007»
15 years 7 months ago
Combining Collective Classification and Link Prediction
The problems of object classification (labeling the nodes of a graph) and link prediction (predicting the links in a graph) have been largely studied independently. Commonly, obje...
Mustafa Bilgic, Galileo Namata, Lise Getoor
142
Voted
COR
2007
106views more  COR 2007»
15 years 3 months ago
Scheduling parallel CNC machines with time/cost trade-off considerations
When the processing times of jobs are controllable, selected processing times affect both the manufacturing cost and the scheduling performance.A well-known example for such a cas...
Sinan Gurel, M. Selim Akturk