2021-03-08 (MAJOR UPDATE)

Changelog

• Moved some of the more advanced material on Bayesian inference (eg VI, MCMC) to vol 2.
• Moved material from the appendices (except for notation) into the main body, integrating some of the material to improve the flow
• Shortened the coverage of Bayesian and frequentist statistics to make more accessible for an intro ML audience
• Reduced page count from 930 to ~825 ("missing mass" will go into vol 2)
• Fixed typos
• Most of the code which is linked to in the figures now runs in colab

2021-03-01 (minor update)

Changelog:

• All figure captions now correctly point to colab code cells
• Fixed various typos (see github issues)

2021-02-07 (minor update)

• fixes many typos

• now the figure captions have pointers to the code using the following kind of URL: figures.probml.ai/book1/3.2, where 3 is the chapter number, and 2 is the figure number. This URL in turn gets mapped to a colab cell using some magic running on GCP]. This layer of indirection allows for multiple back-end implementations of the same figure (eg TF->JAX) while keeping the URL in the book the same.

• changed asset filename from pml1.pdf to book1.pdf (for implementation reasons)

2021-01-18 (minor update)

• index is finally clickable :)
• changed colors of hyperref (green->blue, easier to read)
• added list of figures after preface (temporary change, for debugging the code)
• tweaks to the backprop section from Mathieu
• fixed some typos

2021-01-15 (minor update)

Fixed a bunch of typos (see github issues).
Cleaned up the missing data section, and the decision tree intro section, a little bit.

2021-01-06 (medium update)

• added notation chapter to appendix (this changes the numbering of the appendices!)
• rewrote backprop/ autodiff section (in MLP chapter)
• fixed numerous typos (see closed github issues)
• added a few more references

2021-01-03 (minor update)

Fixed a whole bunch of typos (see closed github issues for details :)

2020-12-31

Several small updates to 2020-12-28 release:

• Fixed all cross-referencing errors.
• Fixed hyper-link to notebooks.
• Fixed some typos reported on github.
• Added back the section on RKHS.
• Added back the section on maxent.
• Added a short section on non-identifiability for Bayesian GMMs.
• Andrew Wilson added a short section on flows for SSL.
• Other random tweaks.

2020-12-28

This release adds the exercises, and fixes some typos.