Errata

Designing Machine Learning Systems

Errata for Designing Machine Learning Systems

Submit your own errata for this product.

The errata list is a list of errors and their corrections that were found after the product was released.

The following errata were submitted by our customers and have not yet been approved or disproved by the author or editor. They solely represent the opinion of the customer.

Color Key: Serious technical mistake Minor technical mistake Language or formatting error Typo Question Note Update

Version Location Description Submitted by Date submitted
Chapter 4 Training Data, "Sampling"
The equation for Importance Sampling

The last term of the derivation should not have "x" between the square brackets. "x" is already absorbed into the expectation E_Q(x) per definition of expectation.

Daniel Wu  Dec 11, 2022 
PDF Page Chapter 6. Model Development and Offline Evaluation
4th paragraph

In "Chapter 6. Model Development and Offline Evaluation", on the 4th paragraph, the author wrote "slide-based evaluation" instead of "slice-based evaluation".

Mustafa Murat Arat  Feb 26, 2023 
PDF Page Chapter 6. Model Development and Offline Evaluation
4th paragraph

In "Chapter 6. Model Development and Offline Evaluation", on the 4th paragraph, the author wrote "slide-based evaluation" instead of "slice-based evaluation".

Mustafa Murat Arat  Feb 26, 2023 
PDF Page p.50
2nd paragraph, first sentence

The second paragraph opens with "Knowing how to collect, process, store, retrieve, and process an increasingly growing amount of data" and while it often seems like you are processing and processing data I don't think it should be in there twice, even if you process it at different places in the process.

Anonymous  Mar 23, 2023 
PDF Page p 122
last sentence of page

Where it reads "you might need subject matter expertise with banking and frauds to be able to come up with useful features" it should probably read "banking and fraud".

Anonymous  Mar 27, 2023 
Mobi Page Chapter 5 - "Common Feature Engineering Operations" - "Scaling"
3rd paragraph

"This process is called feature scaling (...) Neglecting to do so can cause your model to make gibberish predictions, especially with classical algorithms like gradient-boosted trees and logistic regression"

Trees (gradient-boosted or not) are insensitive to scaling of the input values. They should not be used as an example of an algorithm whose performance is improved by scaling input features.

Pedro Osorio  Jun 30, 2023 
Printed Page 25
2nd paragraph

In the second sentence its written "an ML system[...]" which I think should be "a ML system[...]".

Prakash Chaudhary  Dec 13, 2022 
PDF Page 62
2nd paragraph in text box

I think the word "with" is missing at the end of the sentence "You give the system your data (inputs and outputs) and specify the number of models you want to experiment."

Anonymous  Mar 23, 2023 
ePub Page 152
Figure 4-3

The percentage should be either 0.63 or 63%, but it is actually 0.63% which is incorrect

Igor  Jul 25, 2022 
Printed Page 242
Footnote 29

In the printed version of the book, footnote 29 reads “…as the last layer for your classification tax”. Tax is a typo and should be “task” instead.

Daniel Levenson  Jan 23, 2023