Hank O'Brien

About Me

Hey, I'm Hank! I'm a second year student at UC Berkeley and I'm interested in machine learning and software engineering. In my free time, you can probably find me building a robot, working on a side project, catching up on Netflix, or hanging out with friends. I love working on interesting projects, so if you're a developer with a cool side project, send me an email; I'd love to discuss it with you.

One of my hobbies is trying good food. I'm a big foodie, so I like to be on the lookout for tasty recipes I'd like to try. I'm generally a fan of well prepared vegetables, fish, and especially chocolate; I'm a big fan of desserts!

Skills

Highly Experienced

Java

Python

Git

JUnit

SQL (SQLite)

Experienced

Scheme

JavaFX

TensorFlow

MATLAB

Bash Shell

Things I'm Learning

NodeJS

ReactJS

Javascript/Typescript

Parallelism

Electron

Projects

Stella

2017

I helped develop Stella as part of Launchpad last semester. Stella is a Chrome extension that adds a voice assistant to your browsing session. With it, users can do things like look up music, open and close tabs, and otherwise interact with their browser; all from across the room. This project uses a Naive Bayes algorithm to figure out how to act on user queries, and we plan on adding a recurrent neural network to improve on the speech-to-text component in the near future.

Quadris

2016

This is a self-playing Tetris agent which learned to play through a Genetic Algorithm. I built both the learning algorithm and the Tetris game as a final project with my friend in our AP computer science class. I choose this project because I wanted to learn more about machine learning and I thought it would be good to get real-world experience. After about 15 epochs of training, our algorithm outperformed humans on average, though it had a significant standard deviation in its performance.