Artificial Intelligence (AI) technology's rapid advancement has significantly changed various
industries' operations. This comprehensive review paper aims to provide readers with a …

Estimating the structure of directed acyclic graphs (DAGs, also known as Bayesian
networks) is a challenging problem since the search space of DAGs is combinatorial and …

The problem of respiratory sound classification has received good attention from the clinical
scientists and medical researcher's community in the last year to the diagnosis of COVID-19 …

We previously have applied deep autoencoder (DAE) for noise reduction and speech
enhancement. However, the DAE was trained using only clean speech. In this study, by …

Algorithms have never been more important. As the recipes of computer programs,
algorithms rule our lives. Although they can be forces for both good and evil, this is not a …

What do auto-encoders learn about the underlying data-generating distribution? Recent
work suggests that some auto-encoder variants do a good job of capturing the local manifold …

We introduce Devito, a new domain-specific language for implementing high-performance
finite-difference partial differential equation solvers. The motivating application is exploration …

We address the problem of visual classification with multiple features and/or multiple
instances. Motivated by the recent success of multitask joint covariate selection, we …

We describe, analyze, and experiment with a framework for empirical loss minimization with
regularization. Our algorithmic framework alternates between two phases. On each iteration …

We generalize Newton-type methods for minimizing smooth functions to handle a sum of two
convex functions: a smooth function and a nonsmooth function with a simple proximal …