COLT
1998
Springer
13 years 11 months ago
1998
Springer
COLT
1998
Springer
13 years 11 months ago
1998
Springer
COLT
1998
Springer
13 years 11 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...
COLT
1998
Springer
13 years 11 months ago
1998
Springer
Most of the work which attempts to give bounds on the generalization error of the hypothesis generated by a learning algorithm is based on methods from the theory of uniform conve...
COLT
1998
Springer
13 years 11 months ago
1998
Springer
Empirical studies of multitask learning provide some evidence that the performance of a learning system on its intended targets improves by presenting to the learning system relat...
COLT
1998
Springer
13 years 11 months ago
1998
Springer
This paper concerns the use of real-valued functions for binary classification problems. Previous work in this area has concentrated on using as an error estimate the `resubstitut...
COLT
1998
Springer
13 years 11 months ago
1998
Springer
ICML
1998
IEEE
13 years 11 months ago
1998
IEEE
We present and solve a real-world problem of learning to drive a bicycle. We solve the problem by online reinforcement learning using the Sarsa( )-algorithm. Then we solve the ...
ALT
1998
Springer
13 years 11 months ago
1998
Springer
ALT
1998
Springer
13 years 11 months ago
1998
Springer
Exact learning of half-spaces over finite subsets of IRn from membership queries is considered. We describe the minimum set of labelled examples separating the target concept from ...