We present a novel method for unsupervised classification, including the discovery of a new category and precise object and part localization. Given a set of unlabelled images, som...
Leonid Karlinsky, Michael Dinerstein, Dan Levi, Sh...
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...
We propose a hybrid approach to coordinate structure analysis that combines a simple grammar to ensure consistent global structure of coordinations in a sentence, and features bas...
We present a method for computing normals and colors from multiple sets of photometric data, that are consistent with each other and an underlying lower resolution mesh. Normals a...
Local minima and plateaus pose a serious problem in learning of neural networks. We investigate the hierarchical geometric structure of the parameter space of three-layer perceptr...