Skip to content

Bayesian Learning and Neural Networks (jupyter book sources)

License

Notifications You must be signed in to change notification settings

phuijse/BLNNbook

Repository files navigation

Bayesian Learning and Neural Networks

A book on Bayesian Learning and Neural Networks covering theoretical foundations and implementations using Python libraries. This book is published at http://phuijse.github.io/BLNNbook and it sources can be found at http://github.com/phuijse/BLNNbook. This book is constantly evolving, feel free to contact me via phuijse at inf dot uach dot cl or by writing issues in this repo

This book was originally made for the students of the INFO320 course at the Master on INformatics (MIN) program, UACh.

Course abstract

In this course we will study probabilistic programming techniques that scale to massive datasets (Variational Inference), starting from the fundamentals and also reviewing existing implementations with emphasis on training deep neural network models that have a Bayesian interpretation. The objective is to present the student with the state of the art that lays at the intersection between the fields of Bayesian models and Deep Learning through lectures, paper reviews and practical exercises in Python

References

For a deeper theoretical view on the topics found in this book I recommend:

For more a technical view I suggest reading/watching:

For a more general view on Machine Learning I suggest:

  • Murphy, K. P. (2012). Machine learning: a probabilistic perspective. MIT press.
  • Theodoridis, S. (2015). Machine learning: a Bayesian and optimization perspective. Academic press.