2566 search results - page 124 / 514 » Relating reinforcement learning performance to classificatio... |
128
click to vote
ICMLA
2009
15 years 2 months ago
2009
Abstract--This paper presents a novel and domainindependent approach for graph-based structure learning. The approach is based on solving the Maximum Common SubgraphIsomorphism pro...
151
click to vote
LREC
2010
15 years 5 months ago
2010
Existing approaches to classifying documents by sentiment include machine learning with features created from n-grams and part of speech. This paper explores a different approach ...
142
click to vote
IBERAMIA
2010
Springer
15 years 2 months ago
2010
Springer
Reinforcement Learning is commonly used for learning tasks in robotics, however, traditional algorithms can take very long training times. Reward shaping has been recently used to ...
154
click to vote
AIRS
2006
Springer
15 years 8 months ago
2006
Springer
Many text documents naturally have two kinds of labels. For example, we may label web pages from universities according to their categories, such as "student" or "fa...
170
click to vote
ICB
2007
Springer
15 years 8 months ago
2007
Springer
Abstract. In state-of-the-art iris recognition systems, the input iris image has to be compared with a large number of templates in database. When the scale of iris database increa...