Matthew Rahtz

Jupyter notebook running through basic examples of Distributed TensorFlow

mrahtz

Easy TensorFlow logging for quick prototypes

mrahtz

JavaScript/Web Audio implementation of Karplus-Strong guitar synthesis

mrahtz

Reproduction of OpenAI and DeepMind's "Deep Reinforcement Learning from Human Preferences"

mrahtz

Plot TensorBoard graphs fast

mrahtz

A simple moving dot environment for OpenAI Gym to test reinforcement learning algorithms

mrahtz

Jupyter notebook on Gumbel-max and Gumbel-softmax tricks

mrahtz

Differentiate notes using a spiking neural network

mrahtz

TensorFlow implementation of asynchronous advantage actor-critic (A3C)

mrahtz

Code for machine learning workshop given to Sanger Systems group

mrahtz