530 search results - page 28 / 106 » An Introduction to Transfer Learning |
IJCAI
2007
14 years 11 days ago
2007
The options framework provides a method for reinforcement learning agents to build new high-level skills. However, since options are usually learned in the same state space as the...
NIPS
2008
14 years 11 days ago
2008
We address the problem of learning classifiers for several related tasks that may differ in their joint distribution of input and output variables. For each task, small
DAGM
2009
Springer
14 years 5 months ago
2009
Springer
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...
CSEE
2007
Springer
14 years 5 months ago
2007
Springer
Many university classes and commercial training courses rely on classroom lecture and practice exercises to help students learn new skills. The thesis work described in this paper...
IJCAI
2007
14 years 11 days ago
2007
A long-lived agent continually faces new tasks in its environment. Such an agent may be able to use knowledge learned in solving earlier tasks to produce candidate policies for it...