3050 search results - page 230 / 610 » On-line Algorithms in Machine Learning |
165
click to vote
ICML
2000
IEEE
16 years 5 months ago
2000
IEEE
Eligibility traces have been shown to speed reinforcement learning, to make it more robust to hidden states, and to provide a link between Monte Carlo and temporal-difference meth...
160
click to vote
ALT
2005
Springer
16 years 1 months ago
2005
Springer
This paper shows how universal learning can be achieved with expert advice. To this aim, we specify an experts algorithm with the following characteristics: (a) it uses only feedba...
155
click to vote
ERCIMDL
2010
Springer
15 years 1 months ago
2010
Springer
Extracting titles from a PDFs full text is an important task in information retrieval to identify PDFs. Existing approaches apply complicated and expensive (in terms of calculating...
133
click to vote
STOC
1993
ACM
15 years 8 months ago
1993
ACM
In this paper, we study the problem of learning in the presence of classification noise in the probabilistic learning model of Valiant and its variants. In order to identify the cl...
115
click to vote
ICML
2005
IEEE
16 years 5 months ago
2005
IEEE
For Hidden Markov Models (HMMs) with fully connected transition models, the three fundamental problems of evaluating the likelihood of an observation sequence, estimating an optim...