Policy search is a successful approach to reinforcement learning. However, policy improvements often result in the loss of information. Hence, it has been marred by premature conv...
Many people do not read easily for all sorts of reasons: social and cultural, because of impairments, or because of their context. Even in the area of impairments, design for peop...
Caroline Jarrett, Katie Grant, B. L. William Wong,...
One of the main problems faced by university students is deciding the right learning path based on available information such as courses, schedules and professors. In this context,...
We study the problem of correcting spelling mistakes in text using memory-based learning techniques and a very large database of token n-gram occurrences in web text as training d...
When performing discussion search it might be desirable to consider non-topical measures like the number of positive and negative replies to a posting, for instance as one possibl...