0
$\begingroup$

I am following this article about neural networks.

Given:

enter image description here

enter image description here

enter image description here

enter image description here

Until here I understand everything, but then he continues to:

enter image description here

I don't understand how he got to that conclusion. I think he skipped some algebra steps that would have made it easier for me to understand.

$\endgroup$
3
$\begingroup$

We know that:

(1) $\frac{\partial}{\partial x}\big (f(x) + g(x) \big) = \frac{\partial}{\partial x}f(x) + \frac{\partial}{\partial x}g(x)$

(2) $\frac{\partial}{\partial x}a = 0$

Now,

\begin{align*} &\frac{\partial}{\partial w_{12}^{1}} (w_{11}^{1}h_1^{2} + w_{12}^{1}h_2^{2} + w_{13}^{1}h_3^{2} + b_1^{1}) = & \text{[using (1)]}\\ &\frac{\partial}{\partial w_{12}^{1}} (w_{11}^{1}h_1^{2}) + \frac{\partial}{\partial w_{12}^{1}} (w_{12}^{1}h_2^{2}) + \frac{\partial}{\partial w_{12}^{1}} (w_{13}^{1}h_3^{2}) + \frac{\partial}{\partial w_{12}^{1}} b_1^1) = & \\\\ & \text{since } h_1^2 \text{ is independent of } w_{12}^1 \text{ , } h_3^2 \text{ is independent of } w_{12}^1 \text{ , } b_1^1 \text{ is independent of } w_{12}^1 & \text{[using (2)]}\\ & = 0 + \frac{\partial}{\partial w_{12}^{1}} (w_{12}^{1}h_2^{2}) + 0 + 0 \implies \frac{\partial}{\partial w_{12}^{1}} (w_{12}^{1}h_2^{2}) \end{align*}

| improve this answer | |
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.