Chapter 13 typo

[rickiepark]

(p441) In 3rd paragraph, "we can set values for the weight decay contant.." should be "we can set values for the learning rate decay contant..". As you know, SGD's decay param is learning rate decay, not weight decay.

[vmirly]

Thank you for your comment! Yes, that's right! In Keras the decay parameter is for the learning rate decay, whereas in other frameworks (like pytorch for example) they also have weight_decay parameter! We will fix that in future editions. 

Thanks again!

[rickiepark]

(p446) In softmax eq., \sum_{i=1}^M e^{z_j} should be \sum_{j=1}^M e^{z_j}

Thanks.