projects

minimum viable experiment series

generative models and unsupervised learning for videos

subpixel

Enhance! A neural network for image superresolution. This project hit the front page of Hacker News and Trending on Github.

pymerkletools

learning a driving simulator

self coloring books

deep learning for self-driving cars

EEG analysis for Brain Machine Interface

Information Theoretic Learning Autoencoders

RGB-D object recognition

ECG analysis

My undergrad and master research was on blind source extraction. We had ECG recordings from a pregnant woman and we had to separate the ECG signal of the fetus from the signal of the woman. I used kernels methods back then. You kids don't know that anymore, but kernels used to be cool.

Keras contributor

Keras' community is awesome! I contribute with both Tensorflow and Theano code to the source. Some advanced contributions include Neural Turing Machines and Spatial Transformer Networks.

Hubot Recognizer

deep learning with python

publications

papers, in the end of the day I write machine learning papers for a living