Sciweavers

986 search results - page 44 / 198
» Zero-data Learning of New Tasks
Sort
View

Presentation
2959views
15 years 5 months ago
How to Come Up with New Research Ideas in Computer Vision
Computer vision has been studied for more than 40 years. Due to the increasingly diverse and rapidly developed topics in vision and the related fields (e.g., machine learning, sign...
Jia-Bin Huang
ECIS
2000
14 years 11 months ago
The Learning Administration - Shaping Change and Taking Off into the Future
- E-services will change the future of business as well as private relationships. The rearrangement of value chains, new competitive arenas and the growing necessity and interest i...
Hans-Jörg Bullinger, Werner Brettreich-Teichm...
DAGM
2009
Springer
15 years 4 months ago
Learning with Few Examples by Transferring Feature Relevance
The human ability to learn difficult object categories from just a few views is often explained by an extensive use of knowledge from related classes. In this work we study the use...
Erik Rodner, Joachim Denzler
ICML
1998
IEEE
15 years 10 months ago
RL-TOPS: An Architecture for Modularity and Re-Use in Reinforcement Learning
This paper introduces the RL-TOPs architecture for robot learning, a hybrid system combining teleo-reactive planning and reinforcement learning techniques. The aim of this system ...
Malcolm R. K. Ryan, Mark D. Pendrith
CORR
2006
Springer
99views Education» more  CORR 2006»
14 years 9 months ago
PAC Learning Mixtures of Axis-Aligned Gaussians with No Separation Assumption
Abstract. We propose and analyze a new vantage point for the learning of mixtures of Gaussians: namely, the PAC-style model of learning probability distributions introduced by Kear...
Jon Feldman, Ryan O'Donnell, Rocco A. Servedio