projects
minimum viable experiment series Like single file experiments to trully grok things? I got you with Reinforcement Learning and Evolution Stratagies tutorials.
generative models and unsupervised learning for videos I wrote Recurrent Winner-Take-All and Perception Updating Networks. Those methods show how to learn features by exploiting temporal context and to predict future frames in a video (think video compressor or robot planning).
subpixel
Enhance! A neural network for image superresolution. This project hit the front page of Hacker News and Trending on Github.
pymerkletools
I love bitcoin and blockchain! I wrote Tierion's pymerkletools for creating Merkle trees, generating merkle proofs, and verification of merkle proofs.learning a driving simulator
I trained generative adversarial and recurrent neural networks to simulate highway videos.self coloring books
A segmentation network for self driving car data pipelinedeep learning for self-driving cars
CNN+RNN model for deciding where the car should go during Summer at comma.aiEEG analysis for Brain Machine Interface
I wrote the CSP pipeline for EEG analysis in Theano and fine-tuned everything end-to-end. I could've won BCI competition 2 T_TInformation Theoretic Learning Autoencoders
I want to use deep information theoretic learning to compress and make images look pretty.RGB-D object recognition
I trained convnets to recognize objects in 3D when interning with Paracosm.ioECG 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
I put some deep learning on Slackdeep learning with python
video course about deep learning. Mostly using Keras and Theano.publications
papers, in the end of the day I write machine learning papers for a living