Skip to main content

Owen Dugan

Owen Dugan

Age: 18
Hometown: Sleepy Hollow, NY

Technology: “Interpretable Neuroevolutionary Models for Machine Learning”

About Owen

I was a homeschooled student, attending Stanford Online High School fulltime while also studying independently and with mentors. I completed over 20 AP and university-level classes including quantum computing and automata theory. I will study physics and computer science this fall at MIT. I enjoy mountain biking, sailing, and playing piano, guitar, and basketball.

Skip testimonial carousel

"I am honored to be a Davidson Fellow, to have my work nationally recognized, and to join the Davidson Fellows’ community."

Project Description

Despite its benefits, deep learning is not currently employed for many important applications. Because neural networks are so complicated and can fail unexpectedly when presented with data outside their training range, people hesitate to apply this revolutionary technology, particularly when the stakes are high. High-risk and high-precision fields such as medicine and physics, therefore, are failing to reap the full benefits deep learning can provide; I am working to change that by making more interpretable neural networks. For my project, I developed several new techniques to improve and expand the scope of OccamNet, a new interpretable neural network architecture, with the goal of increasing adoption of interpretable and reliable machine learning techniques.

Deeper Dive

My novel techniques, as applied to OccamNet, enable the novel architecture to fit functions with constants, something OccamNet could not previously do, and fit a wider range of implicit equations more effectively. Fitting functions with constants is essential to nearly all applications of interpretable neural networks, and fitting implicit equations is helpful for unsupervised learning and also for modeling many relationships that arise in nature. Thus, by extending OccamNet’s abilities in these two classes of functions, I expanded this new architecture’s scope, rendering a novel approach to interpretable neural networks more effective. In fact, with my new approach, OccamNet is able to fit any class of function, even outperforming the state-of-the-art implicit equation fitting technique on many equations and performing better than the state-of-the-art symbolic regression algorithm across numerous real-world datasets. These results establish my version of OccamNet as a promising candidate in the field of symbolic regression. Importantly, my improved OccamNet architecture is both interpretable and generalizes more effectively outside of the training data range than standard neural networks, therefore contributing to the greater adoption of interpretable and reliable machine learning techniques.

I was drawn to the challenge of neural network interpretability after reading both technical and philosophical papers that detailed the problems of uninterpretable neural networks and the resultant enormous, untapped potential of deep learning. When I was later accepted to the Research Science Institute (RSI) and asked what problem I found most interesting, the answer was clear.

Fortunately, a research group at MIT was working on a novel interpretable neural network architecture (OccamNet) and, seeing my experience with computer science and math, the group offered to mentor me through the RSI program. During RSI (which was conducted virtually due to the COVID-19 pandemic), I made contributions that were significant.


What is your absolute dream job?

I really want to work on AI research at an AI lab, preferably with enough free time to dabble in Theoretical Physics on the side.

What’s the best thing you’ve bought so far this year?

Probably my drop seat for my mountain bike! It has been really nice being able to raise and lower my seat with just a button press, and it has made mountain biking a lot more fun!

If you could be on any TV show, which one would it be?

Scooby Doo! It’s got lots of fun adventures and nobody ever gets hurt! Plus, it would be fun to meet Shaggy and Scooby 🙂

Click image to download high resolution files

In The News

New York – The Davidson Fellows Scholarship Program has announced the 2021 scholarship winners. Among the honorees are 18-year-old Patryk Dabek of East Rutherford, N.J. and 18-year-old Owen Dugan of Sleepy Hollow, N.Y. Only 20 students across the country to be recognized as scholarship winners each year.

Download the full press release here