0
$\begingroup$

enter image description here

I'm implementing the code of this abstraction.

The forward is easy and looks like that: enter image description here

I don't understand the backward path and how it fit's the abstraction in the first image:

enter image description here

  1. Why is db defined as multiplication of ones of x's shape and dout ?
  2. Why is dw defined as multiplication of ones of x.T and dout ?
  3. Why both of them are accumulated. i.e it is used += and not = ?
  4. Why is dw defined as multiplication of ones of dout and w.T ?
$\endgroup$
1
$\begingroup$
  1. This is because the derivative wrt $b$ is $1$: $\frac{\partial E}{\partial b} = 1$
  2. dout is the derivative of loss function wrt prediction. Using chain rule, $$ \frac{dE}{dw} = \frac{dE}{dy}\frac{dy}{ds}\frac{ds}{dw} $$ The last term is the vector of input features $x$. In your case dout is the combination of the first two terms. For example, for MSE loss and sigmoid activation dout $= (y-L)y(1-y)$
  3. This is often used in optimizers for momentum calculation
  4. For MLPs, you need to compute gradients for coarse layers using gradients of deep layers. For example, for MLP with one hidden layer with features $\mathbf{z}$ (hence 3 in total) vector of gradients wrt weights in the input layer $\mathbf{w}^0$ would be $$ y= \sigma(\sum_kw^1_k \cdot\sigma(\sum_jw^0_jx_j))\\ \frac{\partial E}{\partial \mathbf{w^0}} = \frac{\partial L}{\partial y} \frac{\partial y}{\partial s} \frac{\partial s}{\partial \mathbf{z}}\frac{\partial \mathbf{z}}{\partial \mathbf{w}^0} = \frac{\partial E}{\partial \mathbf{z}}\frac{\partial \mathbf{z}}{\partial \mathbf{w}^{0}}\\ \frac{\partial E}{\partial \mathbf{w^0}} = (y-L) y(1-y) \sum_j\frac{\partial s}{\partial z_j}\frac{\partial z_j}{\partial \mathbf{w^0}} = (y-L) y(1-y) \sum_j\frac{\partial s}{\partial z_j}\frac{\partial z_j}{\partial s_j}\sum_i \frac{\partial s_j}{\partial w_{ij}}\\ \frac{\partial E}{\partial \mathbf{z}} = (y-L)y(1-y)\frac{\partial s}{\partial \mathbf{z}} = (y-L)y(1-y)\mathbf{w}^1 $$ So, in other words, in order to compute gradients for weights in the input layer, you need gradients wrt neurons in the hidden layer
$\endgroup$

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.