Joe Palermo's repositories
reinforcement-learning-experiments
Implementations to supplement my reading of "Reinforcement Learning: An Introduction" by Richard S. Sutton and Andrew Barto.
image-captioning
Experiments in image captioning. Classify MNIST sequences with a hybrid CNN-RNN architecture implemented in Pytorch.
nn-fundamentals
Implementations of neural nets from scratch
allennlp
An open-source NLP research library, built on PyTorch.
allennlp-models
Officially supported AllenNLP models
chantools
A loose collection of tools all somehow related to lnd and Lightning Network channels.
fast-ai
Implementations for the fast.ai course. Identifying distracted drivers in dash cam images.
game-playing
Implementations of adversarial games and algorithms for playing them.
math-notes
Notes from math books.
nand2tetris
Projects from the nand2tetris course, http://www.nand2tetris.org/.
neural-networks-and-deep-learning
Some modifications to the code samples from Michael Nielsen's book 'Neural Networks and Deep Learning'
nlp-utilities
Utilities for NLP projects.
openai-cookbook
Examples and guides for using the OpenAI API
q-learning-experiments
An implementation of Q-learning with a "gridworld" environment. An agent is embedded in a grid, and through Q-learning it learns to find its way to a goal. A PyGame animation is included to generate before-learning and after-learning comparisons of the agent's behaviour.
requests-for-research
Implementations related to OpenAIs request for research (https://openai.com/requests-for-research/).
spinningup
An educational resource to help anyone learn deep reinforcement learning.
tensorflow-ffn
A tensorflow clone of Michael Nielsen's network3.py.
theano-rnn
An implementation of a recurrent neural network in Theano.
uncertainty
Implementations of machine learning algorithms that enable modelling uncertainty.