Meet ML@GT: Andrew Sedler on Improving Neuroprosthetic Devices

The Machine Learning Center at Georgia Tech (ML@GT) is home to many talented students from across campus, representing all six of Georgia Tech’s colleges and the Georgia Tech Research Institute (GTRI).

These students have diverse backgrounds and a wide variety of interests both inside and outside of the classroom. Today, we’d like you to meet Andrew Sedler, a machine learning Ph.D. student whose desire to work on difficult problems with clever colleagues drew him not only to machine learning, but to earning a doctorate degree in the field.

Name: Andrew Sedler

Hometown: Greenville, S.C.

Major: Third-year machine learning Ph.D. student in the Wallace H. Coulter Department of Biomedical Engineering

Advisor: Chethan Pandarinath

Previous degrees earned and from what institutions: Bachelor of Science in Bioengineering from Clemson University

Tell us about your research interests. Where might people be impacted by them in everyday life?

I’m currently working on robust hyperparameter tuning methods for models that denoise neural spiking activity from brain recordings. The denoised representations that we uncover are useful for basic science and also have applications in brain-computer interfaces, directly impacting people who use neuroprosthetic devices that decode intentions from neural activity. My broader interests include deep learning, interpretability, and dynamical systems.

What drew you to wanting to research these areas?

I really enjoy this area of research because it allows me to study both biological and computational aspects of intelligence while working on technologies that could yield huge quality of life improvements for people with neuroprosthetics.

What motivated or inspired you to pursue your Ph.D.?

My main inspiration was early research experiences in high school and college that reinforced my desire to work on difficult problems with clever colleagues. Even outside of research, I enjoy exploring all of the nuances of a problem before deriving a firm conclusion, and it turns out that’s what earning a Ph.D. is all about!

Earning your Ph.D. requires a lot of work. What has been challenging, rewarding or unexpected about this experience?

One experience that has been all three of these things was switching into the machine learning (ML) program. I started out as a Ph.D. student in biomedical engineering which was a more natural extension of my undergraduate education. In my first year, I took the ML foundations course with Prof. Justin Romberg and was blown away by the problems that could be solved with ML. As a result, I decided to shift the focus of my entire graduate experience and have been thinking about ML ever since.

Why did you choose Georgia Tech?

I was looking for schools with strong biomedical engineering and computing programs. Georgia Tech was a no-brainer for me (pun intended) because it is a top-ranked school in both categories and is heavily invested in data science and machine learning.

What’s your favorite Georgia Tech memory so far?

I was the social chair for Bioengineering and Biosciences Unified Graduate Students (BBUGS) for a year and a half and have planned and/or attended whitewater rafting trips down the Ocoee River in Tennessee every fall since I started at Georgia Tech. We usually have around 70 graduate students stay for the weekend and it’s a great way to make new friends and enjoy the last few days of summer.

What have you been up to during quarantine?

Working and playing from home on the weekdays, but trying to safely spend time outdoors with my girlfriend on the weekends.

Though 2020 seems to have lasted a lifetime, we are still at the beginning of a new decade. What are you most looking forward to in the next 10 years?

In the next few years, I’m really looking forward to completing my Ph.D. After that, it’ll be starting a family and my career in industry, whether it’s joining an established company or starting a new one. Considering the acceleration of ML over the past decade, I’m also excited to see where the field goes in the next 10 years!

What is your proudest accomplishment?

So far, I’m most proud of being awarded a Graduate Research Fellowship from the National Science Foundation during my first year at Georgia Tech. It made me feel like I belonged in grad school and validated a lot of the work that I had put in behind the scenes.

What are some of your hobbies?

In my spare time, I enjoy cooking, running, mountain biking, and listening to podcasts. Some of my favorite podcasts are The Daily, Radiolab, 99% Invisible, and Talking Machines.

When you’re having a bad day, what do you do to make yourself feel better?

My go-to’s are running and meditation. Running always helps to clear my head and meditation helps me to feel present and content in the moment.

If you could time travel to any period of time, where would you go and why?

I’d probably visit the 1980’s because they had some groovy music, but I’d have to come back to 2020 because they didn’t have graphic processing units (GPU.)

What’s your favorite place to study or work and why?

I really miss working on the top floor of Crossland Tower, with the spectacular panoramic view of Georgia Tech’s campus and Midtown.

Why do you think embodying Georgia Tech’s motto of “progress and service” is important, especially in regards to ML and AI?

As researchers and practitioners in ML and AI we must prioritize progress by emphasizing reproducibility in our work so that we can continue to build on firm foundations. We also have the unique privilege and responsibility of working on technologies that have had large-scale effects on society in recent years (e.g. Facebook, Twitter, YouTube, etc.). We need to keep service to our communities in mind so that our field creates a net positive impact.