small medium large xlarge

The latest version of the book is P1.0, released 16 days ago. If you've bought a PDF of the book and would like to update it to this version (for free), visit your home page.

By default this page displays the errata for the latest version of the book. If you have a previous version, select it here:

If you've found a new error, please submit it.

  • Typo
  • Tech. error
  • Suggestion
  • Maybe next edition
  • Not a problem
  • Reported in: P1.0 (01-Apr-20)
  • Fixed: 03-Apr-20, awaiting book release
#86506
Paper page: 1
I have sent the mobi version to my amazon kindle account. I can see the book on my kindle oasis but it does not appear in the library of my kindle on ...more...
Paolo Perrotta says: Paul, I got a reply from my publisher: "we don't support the kindle app on iOS devices. So, he won't be able to read the mobi version on his mac, unfortunately". I'm sorry about that. I wasn't aware of this complication with Kindle platforms, and I find it surprising and annoying. It's an inconvenience to me personally as well, because I also use the Kindle reader on my Mac. :( I'll have to mark it as "Not a problem" (even if I do think it's a problem) because it's not something I can fix as an author.
  • Reported in: P1.0 (26-Mar-20)
  • Fixed: 26-Mar-20, awaiting book release
#86474
PDF page: 17
The plot in page 17 (pizzas vs reservations) does not use the data from the previous (page 16) pizza.txt. Instead of a 4 point plot, unexpectedly a p...more...
Paolo Perrotta says: Hey, Juanjo. Those shown are just the first few lines of the data file–not all of it. The text says so, but it's easy to miss–so I changed it to be a bit more explicit and avoid any confusion. Thank you!
  • Reported in: P1.0 (06-Apr-20)
#86532
PDF page: 24

For the code in 02_first/linear_regression.py, within method train, the "elif" statement will never be executed.--Xiang Zhang

  • Reported in: P1.0 (01-Apr-20)
#86504
Paper page: 258
Q: at location 5703 of the book in the chapter on convolutions you say: "By the same rules, the output of the second layer is a (29, 29, 32) tensor."...more...