Errata
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 |
|---|---|---|---|---|
| Page Location 3098 Location 3098 |
"removing a random sample of examples from the minority class." when talking about SMOTE near Location 3098 (amazon cloud reader) |
Fernando Bueno | Jan 14, 2021 | |
| Page Location 3109 Location 3109 |
"Combining different techniques" last paragraph. Near location 3109. "recall"... alternativelly ... "recall" |
Fernando Bueno | Jan 14, 2021 | |
| Printed | Page Chapter 5 page 204 Second section with code |
“The result is a 2D array…”, it should be “The result is a 3D array…” |
Rodrigo Ávila | Jan 16, 2023 |
| Printed | Page 15 Figure 3-1 |
The y-axis labels are all identical – "20K". |
Anonymous | Aug 28, 2023 |
| Printed | Page 56 2nd paragraph - tip/suggestion denoted by squirrel |
"TrThe Transform pattern" should be "The Transform pattern" |
Arnesh Sahay | Apr 11, 2022 |
| Printed | Page 72 "Convolutional Neural Network Layers", 3rd paragraph |
It states that the scalar value produced after the final pooling step will be 8. Shouldn't it be 127 instead? |
Kimiyasu Morikawa | Mar 11, 2022 |
| Printed | Page 76 Figure 2-25 |
"Convoltion layer" should be "Convolution layer" |
Arnesh Sahay | Apr 11, 2022 |
| Printed | Page 76 Figure 2-25 |
"Incliment_weather" should be "Inclement_weather" |
Arnesh Sahay | Apr 11, 2022 |
| Printed | Page 81 Figure 3-1 |
The first row in the "Precipitation (mm)" column should read "0 - 0.5" but instead reads "0 - 0.05" |
Arnesh Sahay | Apr 11, 2022 |
| ePub | Page 88 1st and 2nd paragraphs |
In the Kindle version of the book, there is a variable name that is incorrect. On page 88, in the part 'Feature cross in BigQuery ML,' there is a feature named 'hour_of_day'. However, in the two code snippets following the definition of the feature name, we see 'hour_of_week' instead of 'hour_of_day'. |
Arash Nabili | Jan 19, 2021 |
| Printed | Page 89 4th paragraph (Multitask learning) |
On the fifth line, "multi task learning" is inconsistent and should read "multitask learning" |
Arnesh Sahay | Apr 11, 2022 |
| Printed | Page 111 3rd paragraph |
"Given this, training a model on a perfect split of the data will lead to tears." - not entirely sure what this means or if it is correct |
Arnesh Sahay | Apr 11, 2022 |
| Printed | Page 135 2nd paragraph |
If we care more that our model is correct whenever it makes a positive class prediction, we'd optimized our prediction threshold for *recall*. |
Anonymous | Oct 13, 2021 |
| Printed | Page 172 2nd paragraph |
There is a reference to a text classification example in "You'll notice in our text classification example above, we set Trainable=True when initializing our TF Hub layer." Not sure if there is a section or image entirely missing, or if it's just a typo, but there is no text classification example present. |
Arnesh Sahay | Apr 25, 2022 |
| Printed | Page 215 footnote |
The ending parenthesis for the positive complaint should be on the fourth line after "...during the week day every day as well." instead of on the last line "...about how popular they are!" |
Arnesh Sahay | Apr 25, 2022 |
| Printed | Page 220 1st paragraph |
"latency-hroughput" should read "latency-throughput" |
Arnesh Sahay | Apr 25, 2022 |
| Printed | Page 253 Figure 6-2 |
"Passanger_count:" should read "Passenger_count:" |
Arnesh Sahay | May 11, 2022 |
| Printed | Page 253 Figure 6-2 |
There should be a line pointing from "Pickup_latitude: InputLayer" to "Euclidean: Lambda" |
Arnesh Sahay | May 11, 2022 |
| Printed | Page 284 2nd paragraph |
"These individual containerized steps together are then chained together" should read "These individual containerized steps are then chained together" |
Arnesh Sahay | May 11, 2022 |
| Printed | Page 291 Figure 6-9 |
"Retain and redeploy model" should read "Retrain and redeploy model" |
Arnesh Sahay | May 11, 2022 |
| Printed | Page 297 Figure 6-12 |
".csv, .tfecord..." should read ".csv, .tfrecord..." |
Arnesh Sahay | May 11, 2022 |
| Printed | Page 308 Figure 6-18 |
"BigQuety, SQL Warehouse" should read "BigQuery, SQL Warehouse" |
Arnesh Sahay | May 11, 2022 |
| Printed | Page 308 Figure 6-18 |
"GCS or S3 Bbucket" should read "GCS or S3 Bucket" |
Arnesh Sahay | May 11, 2022 |
| Printed | Page 311 3rd paragraph |
"ML engineers can therefore deploy and test a new model version on our own" should read "ML engineers can therefore deploy and test a new model version on their own" |
Arnesh Sahay | May 11, 2022 |
| Printed | Page 334 Figure 7-3 |
"Horsepower-140" should read "Horsepower=140" |
Arnesh Sahay | May 12, 2022 |
| Printed | Page 366 Figure 8-2 |
"Define Business Use c\Cases" should read either "Define business use cases" or "Define Business Use Cases" depending on case preference |
Arnesh Sahay | May 12, 2022 |
| Printed | Page 375 Figure 8-5 |
"Data anaysis" should read "Data analysis" |
Arnesh Sahay | May 12, 2022 |
| Printed | Page 377 Figure 8-6 |
"Data anaysis" should read "Data analysis" |
Arnesh Sahay | May 12, 2022 |