Software Engineer at Google Core Machine Learning. Previously, Guest Researcher at the Flatiron Institute Center for Computational Astrophysics. M.S. in Data Science from NYU Center for Data Science.
Astronomical Image Coaddition with Bundle-Adjusting Radiance Fields
December 15, 2022
This paper, my first first author paper, was presented at the 2023 NeurIPS Machine Learning for the Physical Sciences workshop.
ABSTRACT: Image coaddition is of critical importance to observational astronomy. This family of methods consisting of several processing steps such as image registration, resampling, deconvolution, and artifact removal is used to combine images into a single higher-quality image. An alternative to these methods that are built upon vectorized operations is the representation of an image function as a neural network, which has had considerable success in machine learning image processing applications.
Read More...
Million Song Dataset Recommender System
May 15, 2021
Created recommender system using PySpark’s ALS method to learn latent factor representations for users and items. Final model produces top 500 songs for each user and is evaluated on mean average precision. Created comparison to a single-machine implementation using lightfm.
Click Here for Report PDF
Click Here for GitHub Repository
Read More...
Predicting a Spotify Editorial Playlist
November 19, 2020
personal project with goal of using machine learning to classify whether or not a song will be playlisted on Spotify’s ‘undercurrents’ editorial playlist.
Click Here for Full Project
Read More...
Predicting Restaurant Health Violations Using Yelp Reviews: A Machine Learning Approach
December 5, 2020
Abstract — The New York City Department of Health and Mental Hygiene (DOHMH) conducts at least one random inspection of every NYC restaurant per year, creating potential for missed opportunities to improve the health and hygiene of establishments with food safety issues and increased redundancy of inspecting clean restaurants that are following the guidelines satisfactorily. This project aims to identify restaurants who may be in violation of health and safety code using a classification model that learns restaurant inspection data and text data from Yelp consumer reviews.
Read More...
The Loud Women Project
August 1, 2019
Rhodes Institute for Regional Studies fellowship project: website created with Hugo and hosted on Netlify that houses a timeline of Memphis music history told through the stories of the women who paved its way.
https://www.loudwomenproject.com
Read More...
