Gerardo Duran-Martin's repositories
reinforcement-learning
Repository of notes, code and notebooks in Python for the book "Reinforcement Learning: An Introduction" by Richard S. Sutton and Andrew G. Barto
rebayes-mini
Minimalist version of probml/rebayes
gerdm.nabla.mx
Personal Blog
simple-jax
Recipes for machine learning using Jax (as simple as possible)
deep-learning-bishop
Notes and code from the book Deep Learning: Foundations and Concepts by C. Bishop and H. Bishop
gerdm.github.io
Personal site
prediction-learning-games
Notebook and scripts of Prediction, Learning, and Games by Nicolò Cesa-Bianchi
probml-notebooks
Notebooks for "Probabilistic Machine Learning" book
aistats2022
Subspace EKF neural bandit presentation for AIStats 2022
congress_2017
Code and data for the 2017 Actuarial Congress webapp at the "Universiad Marista"
online-bnn-talk
Talk on online learning of Bayesian neural networks
online-learning-talk
Slides for the online-learning-talk from a Bayesian perspective.
Personalized-News-Recommendation
Multi Armed Bandits implementation using the Yahoo! Front Page Today Module User Click Log Dataset
qmul-fire-talk-0323
PhD Fire Talks for the Statistics and Data Science group at QMUL.
toxic-flow-talk
Slides for the "Detecting Toxic Flow" paper