**Numerical Methods for Deep Learning**

February 23, 2018

3pm, MSC W201

Professor Lars Ruthotto

Abstract: One of the most promising areas in artificial intelligence is deep learning, a form of machine learning that uses neural networks containing many hidden layers. Recent success has led to breakthroughs in applications such as speech and image recognition. However, more theoretical insight is needed to create a rigorous scientific basis for designing and training deep neural networks, increasing their scalability, and providing insight into their reasoning.

In this talk, I present a new mathematical framework that simplifies designing, training, and analyzing deep neural networks. It is based on the interpretation of deep learning as a dynamic optimal control problem similar to path-planning problems. We will exemplify how this understanding helps design, analyze, and train deep neural networks that outperform state-of-the-art methods.

The main focus of this talk is on using the new mathematical framework to design more efficient algorithms and software for deep learning, but also provide intuition for why some existing learning algorithms fail. I will give an overview of two recently launched open-source software packages that aim at bridging the gap between computational mathematicians and data scientists towards the goal of scalable and reliable deep learning algorithms.

Bio: I am an assistant professor at Emory University in Atlanta, GA. I received my diploma and my Ph.D. in mathematics from the University of Münster in 2010 and 2012, respectively. Prior to joining Emory, I was a postdoctoral research fellow at the University of British Columbia and, during my PhD, I held positions at the Universities of Lübeck and Münster. My research interests include numerical analysis (particularly numerical methods for optimization, linear algebra, and partial differential equations) and scientific computing with applications in medical and geophysical imaging and machine learning. My research is supported by the National Science Foundation, the Centers for Disease Control and Prevention, and NVIDIA. I am also a senior consultant at Xtract Technology.