A multitask learning framework is developed for discriminative classification and regression where multiple large-margin linear classifiers are estimated for different predictio...
Despite the widespread deployment of client/server technology, there seem to be no tools currently available that are adequate for analyzing and tuning the performance of client/s...
Object recognition systems aiming to work in real world settings should use multiple cues in order to achieve robustness. We present a new cue integration scheme which extends the...
Emerging multi-core processors are able to accelerate medical imaging applications by exploiting the parallelism available in their algorithms. We have implemented a mutual-inform...
Moriyoshi Ohara, Hangu Yeo, Frank Savino, Giridhar...
Performance asymmetry in multicore architectures arises when individual cores have different performance. Building such multicore processors is desirable because many simple cores...
Saisanthosh Balakrishnan, Ravi Rajwar, Michael Upt...