Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Posts
Experimentation with N-Queens and Monte Carlo
Published:
If you have a chessboard, how can you place 8 queens so that none of them are attacking each other? For a board of size N, this is the N-queens problem. We could solve this directly through recursive backtracking; however, I want to see how well we could do with a pure sampling-based approach. Can we treat this “constraint satisfaction” problem as a sampling problem, where the target probability distribution is \(0\) for any boards with attacking queens, and non-zero for “satisfying” boards? For REALLY big boards, sampling-based approaches might be more efficient at finding boards that are nearly optimal.
Robotics Exploration
Published:
I had the opportunity to work with some of the UVA Collaborative Robotics lab’s robots throughout my second semester. I followed several research directions, as I learned about various components of robotic learning.
Detecting Opps (Opponents in Autonomous Vehicles Race)
Published:
Our team is working to incorporate computer vision as an object tracking modality. We’re using a YOLOv5 model to do this, and the most difficult part has been to collect data. We use a semi-automated pipeline to achieve a high quantity of data through auto-labeling, without sacrificing on quantity.
Sparse Autoencoder
Published:
What kinds of useful features can we extract from images?
Sound Camera
Published:
This is a year-long research project I conducted as a high-school senior at the Thomas Jefferson High School for Science and Technology.
publications
Inferring spatial transcriptomics markers from whole slide images to characterize metastasis-related spatial heterogeneity of colorectal tumors: A pilot study
Published in Journal of Pathology Informatics, 2023
We use deep computer vision models to infer spatially-resolved transcriptomics data.
Download here
Spatial Omics Driven Crossmodal Pretraining Applied to Graph-based Deep Learning for Cancer Pathology Analysis
Published in Pacific Symposium on Biocomputing, 2023
We use deep computer vision models to infer spatially-resolved transcriptomics data.
Download here
Deceptive Path Planning via Reinforcement Learning with Graph Neural Networks
Published in International Conference on Autonomous Agents and Multiagent Systems, 2024
We develop robotic path planning methods for adversarial environments using graph neural networks.
Download here