The Author Online Book Forums are Moving

The Author Online Book Forums will soon redirect to Manning's liveBook and liveVideo. All book forum content will migrate to liveBook's discussion forum and all video forum content will migrate to liveVideo. Log in to liveBook or liveVideo with your Manning credentials to join the discussion!

Thank you for your engagement in the AoF over the years! We look forward to offering you a more enhanced forum experience.

memical (3) [Avatar] Offline
#1
hi,

first of all great book - really easy explained.

i have only misunderstanding i would like to clarify:

in ch. 4 Gradient Descent there is the following formula for weight_delta:

weight_delta = delta * input


all clear so far.

then in ch. 5 Generalizing Gradient Descent the text says:
Each weight delta is calculated by taking its output delta and multiplying itby its input.


which is also clear and in line with ch 4.

but the code right beside the text - on page 81 in MEAP V10 - shows:

weight_deltas = ele_mul(delta,weights)


why is the delta multiplied with weigts?

shouldn't it be:

weight_deltas = ele_mul(delta,input)


?
madara (6) [Avatar] Offline
#2
I think so, probably misprint