548 search results - page 48 / 110 » A New Way to Introduce Knowledge into Reinforcement Learning |
106
click to vote
IJCNN
2007
IEEE
15 years 6 months ago
2007
IEEE
— High-order human cognition involves processing of abstract and categorically represented knowledge. Traditionally, it has been considered that there is a single innate internal...
VMV
2008
15 years 1 months ago
2008
Machine learning with few training examples always leads to over-fitting problems, whereas human individuals are often able to recognize difficult object categories from only one ...
ESANN
2003
15 years 1 months ago
2003
Abstract. This paper considers the general problem of function estimation with a modular approach of neural computing. We propose to use functionally independent subnetworks to lea...
132
click to vote
EMNLP
2010
14 years 9 months ago
2010
In this paper, we introduce a method that automatically builds text classifiers in a new language by training on already labeled data in another language. Our method transfers the...
ECML
2005
Springer
15 years 5 months ago
2005
Springer
The multi-armed bandit problem for a gambler is to decide which arm of a K-slot machine to pull to maximize his total reward in a series of trials. Many real-world learning and opt...