Errata

Strengthening Deep Neural Networks

Errata for Strengthening Deep Neural Networks

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. If the error was corrected in a later version or reprint the date of the correction will be displayed in the column titled "Date Corrected".

The following errata were submitted by our customers and approved as valid errors by the author or editor.

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

Version Location Description Submitted By Date submitted Date corrected
Printed, PDF, ePub, Mobi, , Other Digital Version
Page 119
Paragraph following "Increasing Adversarial Confidence"

The word 'they' should be 'the' in the following sentence:

"The FGSM and JSMA methods generate adversarial examples, but because these attacks generate input close to classification boundaries, they attacks may be susceptible to preprocessing or active defense by the target system."

 Katy Warr
 		 Dec 29, 2019 
Printed, PDF, ePub, Mobi, , Other Digital Version
Page 133
3rd paragraph

Typo: the word 'than' is missing 't' in the sentence below.

"In addition, some approaches require greater knowledge of, or access to, the target system han others"

This sentence appears in the source file: ch07_threat.asciidoc

 Katy Warr
 		 Dec 29, 2019 
Printed, PDF, ePub, Mobi, , Other Digital Version
Page 174
Final paragraph

The text accompanying the confusion matrix on P174 is slightly incorrect.

This is what it currently says:
"You can learn quite a lot about a classifier model from its confusion matrix. For example, <<image_ch9_code_confusion_matrix>>
indicates that shirts are the most likely to be misclassified—11% of the time they are misinterpreted by the model
as T-shirts/tops."

The 11% should say 15% (i.e. just change 11 to 15) like this:

"You can learn quite a lot about a classifier model from its confusion matrix. For example, <<image_ch9_code_confusion_matrix>>
indicates that shirts are the most likely to be misclassified—15% of the time they are misinterpreted by the model
as T-shirts/tops."

 Katy Warr
 		 Dec 29, 2019