Building on past results establishing a benefit for using handwriting when entering mathematics on the computer, we hypothesize that handwriting as an input modality may be able to...
Abstract. Many reinforcement learning domains are highly relational. While traditional temporal-difference methods can be applied to these domains, they are limited in their capaci...
Trevor Walker, Lisa Torrey, Jude W. Shavlik, Richa...
Under-sampling is a class-imbalance learning method which uses only a subset of major class examples and thus is very efficient. The main deficiency is that many major class exa...
— This paper reports on an outdoor mobile robot that learns to avoid collisions by observing a human driver operate a vehicle equipped with sensors that continuously produce a ma...
Conventional image categorization techniques primarily rely on low-level visual cues. In this paper, we describe a multimodal fusion scheme which improves the image classification...