We develop a semi-supervised learning method that constrains the posterior distribution of latent variables under a generative model to satisfy a rich set of feature expectation c...
In many applications surfaces with a large number of primitives occur. Geometry compression reduces storage space and transmission time for such models. A special case is given by...
Abstract. Mechanical ventilation can cause severe lung damage by inadequate adjustment of the ventilator. We introduce a Machine Learning approach to predict the pressure-dependent...
A novel framework for spatially estimating unknown image data is presented. Common applications include inpainting, concealment of transmission errors, prediction in video coding,...
Haricharan Lakshman, Patrick Ndjiki-Nya, Martin K&...
The explanation of a decision is important for the acceptance of machine learning technology in bioinformatics applications such as protein structure prediction. In past research,...
Jieyue He, Bernard Chen, Hae-Jin Hu, Robert W. Har...