In supervised kernel methods, it has been observed that the performance of the SVM classifier is poor in cases where the diagonal entries of the Gram matrix are large relative to ...
Information retrieval tools and search engines have mainly been leveraging research results and technologies developed for the English language. In this paper we report the issues...
Vector quantization methods are confronted with a model selection problem, namely the number of prototypical feature representatives to model each class. In this paper we present a...
Alexander Denecke, Heiko Wersing, Jochen J. Steil,...
This paper develops a weakly supervised algorithm that learns to segment rigid multi-colored objects from a set of training images and key points. The approach uses congealing to ...
Douglas Moore, John Stevens, Scott Lundberg, Bruce...
Our goal is for robots to learn conceptual systems su cient for natural language and planning. The learning should be autonomous, without supervision. The rst steps in building a ...