The Department of Mathematics & Statistics, Kennedy College of Sciences invites you to attend a colloquium talk. This is an in-person event, but Zoom participation is also possible. All are welcome.

This paper introduces a new class of quasi-Newton algorithms for unconstrained minimization in which no line search is necessary and the inverse Hessian approximations are positive definite. These ...

This is a preview. Log in through your library . Abstract We present a readily implementable algorithm for finding stationary points for locally Lipschitzian functions that are not necessarily convex ...

One of the main impacts of learning theory is on engineering. Systems that learn from examples to perform a specific task have many applications 6. For instance, a system may be needed to recognize ...

Machine learning and deep learning have been widely embraced, and even more widely misunderstood. In this article, I’ll step back and explain both machine learning and deep learning in basic terms, ...