M I C H A E L
machine learning
00
machine learning · virginia tech

MICHAEL OWEN

I work in machine learning, from optimizers written
from scratch to real-time computer vision.

currently Data Analyst @ BodBx
studying MS Computer Science ’27
based in Blacksburg, VA
scroll
01 about

I'm a computer science student at Virginia Tech focused on machine learning. Right now I'm training models on athlete movement data, and on the side I build projects like optimizers written from scratch.

5+

years of programming, from C++ to TypeScript

90%+

validation accuracy on a gesture recognition model I built and trained

+35%

accuracy improvement in the Kaggle AI Math Olympiad

2

degrees in progress: BS ’26 & MS ’27, Computer Science

02 skills

What I work with.

a.

Machine Learning

Model design, training, and evaluation

  • PyTorch
  • TensorFlow
  • scikit-learn
  • Pandas
  • NumPy
  • OpenCV
  • MediaPipe
  • Jupyter
b.

Languages

The languages I use day to day

  • Python
  • TypeScript
  • JavaScript
  • Java
  • C/C++
  • SQL
c.

Web & Frameworks

Building and deploying web apps

  • React
  • Next.js
  • Express.js
  • Tailwind
  • Netlify
  • Git
03 selected work

Things I've built.

001

ML Playground

An interactive site for learning six core ML algorithms. I implemented OLS, gradient descent, SGD, and Adam from scratch, and each training run can be replayed step by step on a live loss chart.

// built with
  • Next.js
  • React
  • TypeScript
  • Tailwind
  • SVG viz
002

MichaelsMusic

A custom Spotify web player built on the Web Playback SDK. An Express.js backend handles login and API requests, and the app is deployed on Netlify.

// built with
  • JavaScript
  • Express.js
  • Spotify API
  • OAuth
  • Netlify
003

Gesture Recognition

Recognizes hand gestures from a webcam in real time. I trained a neural network to 90%+ validation accuracy across 8 gesture classes, using data augmentation to expand a small training set.

// built with
  • Python
  • TensorFlow
  • OpenCV
  • MediaPipe
  • CNN
004

Kaggle AI Math Olympiad

A Kaggle competition on solving olympiad-level math problems with ML. I built three PyTorch models and improved accuracy by 35% with ensembling and hyperparameter tuning.

// built with
  • PyTorch
  • Ensembles
  • Feature engineering
  • Tuning
see everything on github ↗
04 experience

Where I've been.

2026 to now

Data Analyst · BodBx

I collect movement data from Virginia Tech athletes with the Strength & Conditioning program and train models to find connections between weight-room training and competition results.

2020 to 2025

Athletics Manager · Highlands Swim & Tennis

Organized 20+ competitions a year and coached 30+ youth athletes over five summers.

2022 to 2027

Virginia Tech · BS + MS Computer Science

Bachelor's expected May 2026, accelerated Master's expected May 2027. Focus on machine learning and data-driven systems.

05 contact

Let's work together.