Ctrl+K

About this Jupyter Book

About this Jupyter Book#

About these lecture notes#

These lecture notes were originally created by Dick Furnstahl and then modified by Daniel Phillips. The jupyter notebooks were originally developed by Furnstahl, Phillips, and particularly Christian Forssén. The lectures and notebooks are now maintained and updated jointly by Furnstahl and Phillips. They are released under a Creative Commons BY-NC license. The book format is powered by Jupyter Book.

Open an issue

If you find a problem or have a suggestion when using this Jupyter Book (on physics, statistics, python, or formatting), from any page go under the github icon github download icon at the top-middle-right and select “open issue” (you may want to open in a new tab by right-clicking on “open issue”). This will take you to the Issues section of the Github repository for the book. You can either use the title already there or write your own, and then describe in the bigger box your problem or suggestion.

Acknowledgements#

This material originated from an intensive three-week summer school course taught at the University of York in 2019 by Christian Forssén, Dick Furnstahl, and Daniel Phillips as part of the TALENT initiative. The first version of the notes were used to teach a graduate course at The Ohio State University in Autumn 2019 and repeated with updates in Autumn 2021. Daniel Phillips revised the notes when he taught the course in Autumn 2023. Phillips and Furnstahl acknowledge in particular the following colleagues, who played a key role in shaping this course and their understanding of Bayesian statistics.

  • Prof. Christian Forssén, Chalmers University of Technology

  • Prof. Morten Hjorth-Jensen, Oslo University and Michigan State University

  • Dr. Jordan Melendez, Ohio State University and Root Insurance

  • Prof. Matt Plumlee, Northwestern University and Amazon

  • Prof. Matt Pratola, Ohio State University

  • Prof. Frederi Viens, Michigan State University

  • Dr. Sarah Wesolowski, York, UK

We also thank the students and colleagues who have contributed suggestions and comments.

The development of this course also would not have been possible without the knowledge gained through the study of several excellent textbooks, most of which are listed as recommended course literature. Here is a short list of those references that we have found particularly useful as physicists learning Bayesian statistics and machine learning:

[GCS+13] Andrew Gelman et al., “Bayesian Data Analysis, Third Edition”, Chapman & Hall/CRC Texts in Statistical Science (2013).
[Gre05] Phil Gregory, “Bayesian Logical Data Analysis for the Physical Sciences”, Cambridge University Press (2005).
[Jay03] E. T. Jaynes, “Probability Theory: The Logic of Science”, Cambridge University Press (2003).
[Mac03] David J.C. MacKay, “Information Theory, Inference, and Learning Algorithms”, Cambridge University Press (2005).
[SS06] D.S. Sivia with J. Skilling, “Data Analysis : A Bayesian Tutorial”, Oxford University Press (2006).

The presentation and examples in the book by Sivia have been the underlying guide for much of the course. Other valuable references can be found in the Bibliography.

Brief guide to online Jupyter Book features#

  • A clickable high-level table of contents (TOC) is available in the panel at the left of each page. You can toggle this panel open and closed with the contents icon (three horizontal lines) at the upper left.

  • For each section that has subsections, a clickable table of contents appears in the rightmost panel.

  • The “Search this book…” icon is the magnifying glass icon to the far right in the top-middle. Try it!

  • On pages that are not generated from Jupyter notebooks, the other four icons at the top-middle-right will take you to the github repository for the book or let you open an issue (see the top of this page); show you the markdown source (.md) of the page or generate a pdf version of the page; put you into full-screen mode; or toggle light/dark mode.

  • On pages generated from Jupyter notebooks, there is an additional icon at the top-middle-right (leftmost), which enables you to run the notebook on a cloud server using Binder. When running on Binder, be patient; it may take a while to generate the page if the environment needs to be created from scratch (in general it is cached, so it will be much faster if others have been recently using notebooks from the repository).

Short (16 minute) video with overview of this Jupyter Book#

Contents