2263 search results - page 168 / 453 » The Use of Functional and Logic Languages in Machine Learnin... |
170
click to vote
COLT
1998
Springer
15 years 10 months ago
1998
Springer
We introduce and analyze a new algorithm for linear classification which combines Rosenblatt's perceptron algorithm with Helmbold and Warmuth's leave-one-out method. Like...
169
click to vote
ICML
2008
IEEE
16 years 6 months ago
2008
IEEE
We present a reinforcement learning architecture, Dyna-2, that encompasses both samplebased learning and sample-based search, and that generalises across states during both learni...
146
click to vote
FSTTCS
2007
Springer
16 years 5 days ago
2007
Springer
Abstract. We provide a framework for distributed systems that impose timing constraints on their executions. We propose a timed model of communicating finite-state machines, which...
172
click to vote
ICML
2006
IEEE
16 years 6 months ago
2006
IEEE
Policy evaluation is a critical step in the approximate solution of large Markov decision processes (MDPs), typically requiring O(|S|3 ) to directly solve the Bellman system of |S...
136
click to vote
COOTS
2001
15 years 7 months ago
2001
Mainstream object-oriented languages, such as C++ and Java1 , provide only a restricted form of polymorphic methods, namely uni-receiver dispatch. In common programming situations...