Researching neural network efficiency at the intersection of machine learning and hardware design.
I'm a final-year MS/BS student at Worcester Polytechnic Institute working on making neural networks faster, more efficient, and deployable on edge devices. My research spans model compression, neuromorphic computing, and hardware acceleration.
Currently applying to PhD programs for Fall 2026.
Developed semantic segmentation dataset (1,400+ days) for detecting coronal holes on the solar surface. Built custom annotation pipeline and trained progressively growing U-Net models, improving IoU by 15%. Joint first author on paper submitted to Astronomy & Astrophysics.
Under review at Astronomy and Astrophysics
Novel quantization technique for fully binary weight neural networks (including first and last layers) achieving drag and drop 70.19% accuracy on CIFAR-100 with ResNet18 (less than 3% drop from full precision), and 56.6% top 1 accuracy on ImageNet using ResNet18. Uses stochastic mask annealing without surrogate gradients or soft-to-hard weight transformations.
Preparing manuscript
Designing and implementing a spiking neural network accelerator for semantic segmentation on FPGA. Developed a custom Python-to-RTL pipeline with FPGA-specific quantization-aware training (QAT) and a buffered hardware architecture that exploits sparsity in spiking networks.
Targeting low-energy classification and semantic segmentation for autonomous driving applications using the Cityscapes dataset.
Image shows MNIST digit input to the spiking neural network over timesteps, using rate encoding generated at the RTL level with a pixelwise LFSR pseudo-random number generator.
A smaller project, focusing on creating a very small systolic array for the small system on chip (SoC), Croc, on an 180 nm process. This project explores making a systolic array for low power with fp4 and and iterated low power individual processing elements.
This project integrates elements of the systolic array core (sauria core) from Sauria. Our improvement are building upon the existing zero skipping, shift registers, and other improvements from Sauria.
Using a generalized modification of A*, can solve and build from existing Bananagrams boards in seconds.
As part of our cirriculum at Worcester Polytechnic Institute, we do an Interactive Qualifify Project (IQP). My IQP was done in Acadia National Park in Maine, working with the National Park and Friends of Acadia. From IQP we wrote an in depth report of our findings and recommendations.
A small animation using the Python package Manim to show how the small signal model works. In the future, I hope to flesh this explanation out to be more comprehensive.
