Current systems used in education follow a consistent design pattern, one that is not supportive of lifelong learning or personalization, is asymmetric in terms of user capability,...
Scott Wilson, Oleg Liber, Mark Johnson, Phillip Be...
We propose and analyze two strategies to learn over unordered pairs with kernels, and provide a common theoretical framework to compare them. The strategies are related to methods...
In this paper we present the system ALLPAD for learning Logic Programs with Annotated Disjunctions (LPADs). ALLPAD modifies the previous system LLPAD in order to tackle real world ...
This paper describes a novel real-world reinforcement learning application: The Neuro Slot Car Racer. In addition to presenting the system and first results based on Neural Fitted...
This paper studies the problem of learning from ambiguous supervision, focusing on the task of learning semantic correspondences. A learning problem is said to be ambiguously supe...