In typical classification problems, high level concept features provided by a domain expert are usually available during classifier training but not during its deployment. We address this problem from a multitask learning (MTL) perspective by treating these features as auxiliary learning tasks. Previous efforts in MTL have mostly assumed that all tasks have the same input space. However, auxili...

The utility of vision-based face tracking for dual pointing tasks is evaluated. We first describe a 3-D face tracking technique based on real-time parametric motion-stereo, which is non-invasive, robust, and self-initialized. The tracker provides a real-time estimate of a “frontal face ray” whose intersection with the display surface plane is used as a second stream of input for scrolling or po...

this study investigated how awareness affected learners’ intake and production in relation to their cognitive styles. it is assumed that learners’ cognitive styles may affect their ability to notice particular features in the input and, consequently, their intake and production. adult learners of english were exposed to four english structures through four sets of problem-solving tasks, followe...

Multitask learning addresses the problem of learning related tasks whose information on parameters is assumed to be shared with each other. Previous approaches usually deal with homogeneous tasks such as a set of regression tasks only or a set of classification tasks only. In this paper, we consider the problem of learning multiple related tasks, where tasks consist of predicting both continuou...

Most interaction with computers today takes place in a two dimensional environment. Even when using three dimensional graphics applications, input is often still restricted to two dimensions. Many believe that the use of three dimensional input devices will alleviate this restriction and allow for a much more natural human-machine dialog. This thesis seeks to establish how factors dealing with ...