Graduate Projects

These projects are from my Master of Information and Data Science program at UC Berkeley. They reflect my earlier work in machine learning, natural-language processing, computer vision, and deep learning.

Machine Learning Projects

Mountain Project Sentiment Analysis using Transfer Learning and DistilBERT

An end-to-end natural-language processing project that labels sentiment in Mountain Project forum posts to explore which climbing gear users discuss most positively. The project covers web scraping, data cleaning, model selection, transfer learning, and final analysis. Solo project.

Audio Super-Resolution — Thesis Project

A deep-learning project using GANs and autoencoders to upsample low-quality audio in real time. Team project.

Car Damage Detection Part 1 — Image Classification

A comparison of traditional machine-learning approaches and convolutional neural networks for classifying vehicle images as damaged or undamaged. Solo project.

Car Damage Detection Part 2 — Damage

A computer-vision project using Mask R-CNN to identify and localize damaged areas in vehicle images. Team project.