**Ankit B. Patel**

*Asst. Professor*

**Baylor College of Medicine & Rice University**

*Rice:* Duncan Hall 2050, *BCM:* Ben Taub Center, T115F

**E-mail:** abp4 at rice.edu, ankitp at bcm.edu

### About Me

Starting in Jan 2016, I am a new faculty member at the Baylor College of Medicine in the Dept. of Neuroscience, with a joint appointment in the ECE Dept. at Rice University and a courtesy appointment in the Computer Science Dept.

I was a Research Scientist at Rice University, focusing on deep machine learning and computational neuroscience, where I worked with Richard Baraniuk in the ECE Dept. I graduated from Harvard with a Ph.D. in Applied Mathematics and my graduate work was done in the EECS Dept. with Radhika Nagpal. My undergraduate degree was in Computer Science and Applied Mathematics (BA, MS, Harvard 2002).

I spent 6 years in industry working on real-time inference systems, including 2 years at MIT Lincoln Laboratory (2002-2004) and 4 years as a Quantitative Trader at Global Electronic Trading Corporation (2008-12) — a high-frequency market-making firm that is now a part of KCG Holdings. Recently, I decided to return to academia and so I joined Rice in 2013 as a Research Scientist.

My current work tries to shed new light on the successes (and shortcomings) of techniques in modern Deep Learning. The simple question that started this work was: * Why does Deep Learning work?* In order to answer this question, we started by building a probabilistic theory based on a generative model — the Deep Rendering Model (DRM). With the DRM, we can show how to derive Deep Convolutional Nets and, unexpectedly, Random Decision Forests from first principles. For more information, please check out the Projects page for this and other projects I’m involved in.