This paper introduces a new algorithm, Q2, foroptimizingthe expected output ofamultiinput noisy continuous function. Q2 is designed to need only a few experiments, it avoids stron...
Andrew W. Moore, Jeff G. Schneider, Justin A. Boya...
—Active learning can actively select or construct examples to label to reduce the number of labeled examples needed for building accurate classifiers. However, previous works of...
Abstract— We present and examine a technique for estimating the ego-motion of a mobile robot using memory-based learning and a monocular camera. Unlike other approaches that rely...
Richard Roberts, Hai Nguyen, Niyant Krishnamurthi,...
Abstract a paradigm of modern Machine Learning (ML) which uses rewards and punishments to guide the learning process. One of the central ideas of RL is learning by “direct-online...
We address the e-rulemaking problem of reducing the manual labor required to analyze public comment sets. In current and previous work, for example, text categorization techniques...