The latest version of the book is B13.0, released 25 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.
- Reported in: B13.0 (03-Feb-20)
- Fixed: 07-Feb-20, awaiting book release
PDF page: code
The code plot_linearly_separable inside 08_perceptron file should be completed with plt.pause(1) inside def plot after plt.show instruction . Because not work properly when you Run I mean you don't manage see plots. ......With debugger mode it's all ok.
- Reported in: B13.0 (09-Feb-20)
- Fixed: 23-Feb-20, awaiting book release
PDF page: 0000
Running this code ……...code/13_batching/solution/compare_stochastic_gd_learning_rate.py ...…...give this error ...….. code\13_batching\solution\neural_network.py:7: RuntimeWarning: overflow encountered in exp
return 1 / (1 + np.exp(-z))--Leonardo Carotti
- Reported in: B13.0 (01-Feb-20)
- Fixed: 02-Feb-20, awaiting book release
PDF page: 70
At page 58 in pdf the sentence... meaning that they have one row for examples, and one column.. is correct, but at page 70 in pdf, the sentence.... one row for examples, and one column for weight... is not because it would otherwise mean that y_at has a dimension (30,4) but is actually (30,1)
- Reported in: B13.0 (30-Jan-20)
- Fixed: 31-Jan-20, awaiting book release
PDF page: 141
In Chapter 11, at page 141 in pdf version, the sentence .....The next-to-last line calculates (y^- y)*W2*σ ..... have a typography error because the sigmoid is written without accent.--Leonardo Carotti