—This paper presents a new methodology based on evolutionary multi-objective optimization (EMO) to synthesize multiple complex modules on programmable devices (FPGAs). It starts ...
Learning from ambiguous training data is highly relevant in many applications. We present a new learning algorithm for classification problems where labels are associated with se...
There is a problem in the spatial and temporal separation between the varying forms of representation used in urban design. Sketches, physical models, and more recently computatio...
Hiroshi Ishii, Eran Ben-Joseph, John Underkoffler,...
Abstract. In this paper we argue that many of the problems one may experience while visiting websites today may be avoided if their builders adopt a proper methodology for designin...
Abstract. In this work we propose a new method to create neural network ensembles. Our methodology develops over the conventional technique of bagging, where multiple classifiers ...