We propose a family of learning algorithms based on a new form of regularization that allows us to exploit the geometry of the marginal distribution. We focus on a semi-supervised...
We introduce the problem of zero-data learning, where a model must generalize to classes or tasks for which no training data are available and only a description of the classes or...
The prediction of protein secondary structure is a classical problem in bioinformatics, and in the past few years several machine learning techniques have been proposed to t. From...
Gaussian Process Temporal Difference (GPTD) learning offers a Bayesian solution to the policy evaluation problem of reinforcement learning. In this paper we extend the GPTD framew...
Abstract— An ontology is a formal language adequately representing the knowledge used for reasoning in a specific environment. When contradictions arise and make ontologies inad...