Sumedh Hindupur

Namaskaram! (Hello!)

I am Sumedh, a Ph.D. student in Applied Mathematics at Harvard University's School of Engineering and Applied Sciences, working under the supervision of Prof. Demba Ba.

Prior to joining Harvard, I earned a Dual Degree (BTech+MTech) in Electrical Engineering from the Indian Institute of Technology Bombay in August 2023, where I was honored with the Institute Silver Medal for graduating as the Department Topper.
My master's thesis, supervised by Prof. Vivek Borkar, focused on novel approaches for online parameter estimation in Partially Observed Markov Decision Processes (POMDPs).

In my free time, I love playing lawn tennis: I'm an officer at the Harvard Griffin GSAS Tennis Club, and reading novels (recent read: Graeme Simsion's The Rosie Project)

Research Interests

My research lies at the intersection of neural network interpretability, computational neuroscience, and signal processing. I am particularly interested in developing interpretable machine learning frameworks to understand the internal representations of artificial neural networks and brains. See this NEMI poster for my recent work in this direction. Our recent preprint is on understanding the interaction between Sparse Autoencoders and the data they are trained on, which lays the foundation for developing better tools for AI interpretability through greater understanding of the structure of AI model latent representations.

In my prior work, I investigated:

Online parameter estimation in POMDPs [paper] (with Prof. Vivek Borkar, IIT Bombay)
This work introduces a novel methodology for real-time parameter estimation in POMDPs using maximum likelihood estimation integrated with extremum-seeking. The framework enables online learning for sequential decision-making processes with partial observations and is supported by theoretical analyses and extensive numerical validations.
Neural population coding in the mouse visual cortex [paper](in collaboration with Dr. Amin Moosavi, UCLA and Prof. Hideaki Shimazaki, Kyoto University),
This study explores the role of scale-invariant noise structures in high-dimensional neural activity and their implications for population coding. Using large-scale neural recordings from the mouse visual cortex, we identify conditions under which neural populations achieve unbounded information capacity, offering insights into the scalability of neural coding systems.
Spiking neural network architectures [report] (with Prof. Alice Parker, University of Southern California),
We simulated a biologically inspired spiking neural network to tackle catastrophic forgetting in sequential learning tasks. By leveraging mechanisms like dopamine-driven reward learning and synaptic plasticity, the NeuRoBot successfully retained previously learned skills while acquiring new ones. This work bridges neuroscience insights with adaptive AI design.
MEG-based signal analysis of neural activity [report] (with Prof. Ole Jensen and Dr. Yali Pan, University of Birmingham).
We investigated interactions between brain oscillations during reading by analyzing MEG data. Using rapid frequency tagging and statistical tests, we studied subtle interactions between alpha oscillations and high-frequency activity in the visual cortex.

Publications

"Projecting Assumptions: The Duality between Sparse Autoencoders and Concept Geometry"
Sai Sumedh R. Hindupur, Ekdeep Singh Lubana, Thomas Fel and Demba Ba
Preprint on arXiv (2025)
Read the Paper
"Population Coding under the Scale-Invariance of High-Dimensional Noise"
S. Amin Moosavi, Sai Sumedh R. Hindupur, Hideaki Shimazaki
Preprint on bioRxiv (2024)
Read the Paper
"Online Parameter Estimation in Partially Observed Markov Decision Processes"
Sai Sumedh R. Hindupur, Vivek S Borkar
Published at the 59th Annual Allerton Conference on Communication, Control, and Computing (2023)
Read the Paper

Page updated

Google Sites

Report abuse