To learn concepts over massive data streams, it is essential to design inference and learning methods that operate in real time with limited memory. Online learning methods such a...
We build the generic methodology based on machine learning and reasoning to detect the patterns of interaction between conflicting agents, including humans and their assistants. L...
In this paper we introduce the concept and method for adaptively tuning the model complexity in an online manner as more examples become available. Challenging classification pro...
A conversational method of teaching whereby the students engage each other as a key part of the learning experience achieves a higher percentage of high grades (and presumably bet...
We introduce the novel problem of inter-robot transfer learning for perceptual classification of objects, where multiple heterogeneous robots communicate and transfer learned obje...