When we have several related tasks, solving them simultaneously is shown to be more effective than solving them individually. This approach is called multi-task learning (MTL) and...
Typically the response of a multilayered perceptron (MLP) network on points which are far away from the boundary of its training data is not very reliable. When test data points ar...
This paper proposes a distributed platform designed to support pervasive learning and interactivity on a university campus and to ease tasks related to learning and teaching. The ...
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...
We propose a new integrated approach based on Markov logic networks (MLNs), an effective combination of probabilistic graphical models and firstorder logic for statistical relatio...