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)
?
