Side Projects
Here are several side projects that I mainly contributed to in the past few years.

MIT Deep Learning related courses
TA for 6.S094: Deep Learning for Self-Driving Cars and 6.S099: Artificial General Intelligence. Help prepare instruction materials, tutorials, and coding assignments.
(7k stars on Github)

AI Podcast
Help prepare interview questions, search for guest speakers, etc. for a podcast hosted by Dr. Lex Fridman about technology, science, and the human condition.
(ranked #1 on Apple Podcasts in the technology category, 1M views on YouTube)
(My personal favorite episode is with Tomaso Poggio, highly recommended!)

Robocar Workshop
Instructor for a summer/winter workshop at MIT with Dr. Tom Bertalan to college and high school students on building and programming autonomous robocars.


Competitions Expert (highest rank: 1196th | current rank)

Kaggle is an online platform for machine learning competitions. On a side of fun, I'm a casual Kaggler who is interested in playing with various kinds of data. Most of the competitions I attended were for image-related problems, others include numerical data such as insurance and sales prediction, and text data for NLP-related problems.

Statoil/C-CORE Challenge
(Satellite Image Classification)

· 2018 · Top 6%

Data Science Bowl 2017
(Lung Cancer Detection)

· 2017 · Top 6%

Generative Art

Generative Art refers to the kind of art that in whole or in part has been created with the use of an autonomous system. I'm particularly interested in creating artwork using modern computational vision and deep learning methods, a.k.a. Algorithmic Art.

One of the things I've been playing with is Compositional Pattern-Producing Networks (CPPN). The (interactive) canvas below shows how such a deep neural network running in the browser is able to generate exquisite patterns through randomized vector computations. This work is inspired by David Ha's blog post and powered by TensorFlow.js. The source code can be found here.

Compositional Pattern-Producing Networks