In this paper we construct the linear support vector machine (SVM) based on the nonlinear rescaling (NR) methodology (see [9, 11, 10] and references therein). The formulation of t...
We propose a novel objective function for discriminatively tuning log-linear machine translation models. Our objective explicitly optimizes the BLEU score of expected n-gram count...
We present a new approximate inference algorithm for Deep Boltzmann Machines (DBM's), a generative model with many layers of hidden variables. The algorithm learns a separate...
Embedded systems serve an emerging and diverse set of applications. As a result, more computational and storage capabilities are added to accommodate ever more demanding applicati...
SALSA examines system logs to derive state-machine views of the sytem's execution, along with control-flow, data-flow models and related statistics. Exploiting SALSA's d...