rasbt
Wrong index in Fig on page 384?
Hi Sebastian.
On page 384 in the MLP figure there might be a typo? In the 2nd layer for the last activation unit I would have expected the sub-index to be "d", not "h". That would fit also with the (m x d) dimension of W(h) as mentioned on page 389 (first section).
Good catch, you are right! I am just fixing this for the 3rd edition. Many thanks!
No worries, I am glad I could help. When should we expect the third edition to be published?
We are currently aiming for ~mid October. Vahid and I have been working on a bunch of new content (mainly rewriting everything after Ch 12 wrt Tf 2.0 and adding a GAN and reinforcement learning chapter) -- currently, we are going over it a few more times to make sure everything is in good shape. Shouldn't be too long from now on.