We present a general approach to model selection and regularization that exploits unlabeled data to adaptively control hypothesis complexity in supervised learning tasks. The idea ...
— We aim to perform robust and fast vision-based localization using a pre-existing large map of the scene. A key step in localization is associating the features extracted from t...
The high dimensionality of functional magnetic resonance imaging (fMRI) data presents major challenges to fMRI pattern classification. Directly applying standard classifiers often ...
Bernard Ng, Arash Vahdat, Ghassan Hamarneh, Rafeef...
New technologies have recently emerged to challenge the very nature of computing: multicore processors, virtualized operating systems and networks, and data-center clouds. One can...
Several dual-rail logic styles make use of single-rail flip-flops for storing intermediate states. We show that single mask bits, as applied by various side-channel resistant logic...
Amir Moradi, Thomas Eisenbarth, Axel Poschmann, Ch...