nipunbatra / pml-teaching

23 stars 13 forks source link

Slides and Notebooks for my Probabilistic Machine Learning Course

References and Acknowledgments There are several excellent resources I heavily relied on to create this course. I would like to thank the authors of these resources for making them available to the public (in no particular order) 1. Piyush Rai (IIT Kanpur) excellent course and slides on the same subject 2. Philip Hennig (University of Tübingen) excellent course and slides on the same subject 3. Kevin Murphy (Google) excellent book on the same subject 4. Ben Lambert has a great book and [Youtube videos](https://www.youtube.com/playlist?list=PLwJRxp3blEvZ8AKMXOy0fc0cqT61GsKCG) on the same subject 5. Aki Vehtari (Aalto University) excellent course and slides on the same subject 6. Richard McElreath course on Statistical Rethinking 7. Allen Downey (Olin College) excellent book on the same subject 8. Sargur Srihari (University at Buffalo) [excellent course and slides](https://cedar.buffalo.edu/~srihari/CSE574/) on the same subject 9. Felix Machine Learning and Simulation YouTube [channel](https://www.youtube.com/@MachineLearningSimulation)
Course Outline - Introduction and Logistics [[slides](slides/introduction.pdf)][[notebook](notebooks/cats-dogs.ipynb)], [AL notebook], [BO notebook] - Distributions, Refresher [[notebook](notebooks/distributions.ipynb)] - Maximum Likelihood Estimation for Univariate [[slides](slides/mle.pdf)][[notebook](notebooks/mle-univariate.ipynb)] - MLE Multivariate - MAP estimation - Bayesian Inference with conjugate priors - MLE, MAP for Linear Regression - Bayesian Linear Regression - MLE, MAP for Logistic Regression - Bayesian Logistic Regression (with Laplace Approximation for posterior) - Bayesian Logistic Regression (with Probit apprximation for predictive) - Sampling Methods (Monte Carlo, Rejection Sampling) - Markov Chain Monte Carlo (Metropolis-Hastings)