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...
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...
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...
John Case, Sanjay Jain, Matthias Ott, Arun Sharma,...
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...
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 ...
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 ...