Sciweavers

2455 search results - page 10 / 491
» Learning Composite Concepts
Sort
View
ICML
1998
IEEE
14 years 2 months ago
Learning to Drive a Bicycle Using Reinforcement Learning and Shaping
We present and solve a real-world problem of learning to drive a bicycle. We solve the problem by online reinforcement learning using the Sarsa(   )-algorithm. Then we solve the ...
Jette Randløv, Preben Alstrøm
CVPR
2008
IEEE
15 years 2 days ago
Similarity-based cross-layered hierarchical representation for object categorization
This paper proposes a new concept in hierarchical representations that exploits features of different granularity and specificity coming from all layers of the hierarchy. The conc...
Sanja Fidler, Marko Boben, Ales Leonardis
ECTEL
2006
Springer
14 years 1 months ago
Blended Learning Concepts - a Short Overview
This paper presents a short overview of blended learning, showing arguments for and against these concepts. Potential blended learning scenarios are described that vary depending o...
Sonja Trapp
COLT
2001
Springer
14 years 2 months ago
Intrinsic Complexity of Learning Geometrical Concepts from Positive Data
Intrinsic complexity is used to measure the complexity of learning areas limited by broken-straight lines (called open semi-hulls) and intersections of such areas. Any strategy le...
Sanjay Jain, Efim B. Kinber
ICML
2008
IEEE
14 years 11 months ago
Composite kernel learning
The Support Vector Machine (SVM) is an acknowledged powerful tool for building classifiers, but it lacks flexibility, in the sense that the kernel is chosen prior to learning. Mul...
Marie Szafranski, Yves Grandvalet, Alain Rakotomam...