Research on practical design verification techniques has long been impeded by the lack of published and yet detailed error data. Over the last few years we have systematically coll...
David Van Campenhout, Trevor N. Mudge, John P. Hay...
We start by showing that in an active learning setting, the Perceptron algorithm needs Ω( 1 ε2 ) labels to learn linear separators within generalization error ε. We then prese...
Sanjoy Dasgupta, Adam Tauman Kalai, Claire Montele...
In model selection procedures in supervised learning, a model is usually chosen so that the expected test error over all possible test input points is minimized. On the other hand...
Backpropagation, similar to most learning algorithms that can form complex decision surfaces, is prone to overfitting. This work presents classification-based objective functions, ...
This paper explores unexpected results that lie at the intersection of two common themes in the KDD community: large datasets and the goal of building compact models. Experiments ...