Due to its occurrence in engineering domains and implications for natural learning, the problem of utilizing unlabeled data is attracting increasing attention in machine learning....
In many real world applications, labeled data are usually expensive to get, while there may be a large amount of unlabeled data. To reduce the labeling cost, active learning attem...
Chun Chen, Zhengguang Chen, Jiajun Bu, Can Wang, L...
Medical data is often presented as free text in the form of medical reports. Such documents contain important information about patients, disease progression and management, but ar...
Fathi H. Saad, Beatriz de la Iglesia, Duncan G. Be...
We performed an empirical study to investigate whether the context of interruptions makes a difference. We found that context does not make a difference but surprisingly, people c...
We describe our approach and initial results in the participatory design of technology relevant to local rural livelihoods. Our approach to design and usability proceeds from rese...
Kevin Walker, Joshua Underwood, Timothy Mwololo Wa...