Hello,

I perform two forward passes before a single backward pass as follows:

```
y_a = net.forward(image_a)
y_b = net.forward(image_b)
loss.backward()
optimizer.step()
```

I would like to know how concretely does the backward pass take into account both y_a and y_b in the weights update.

I have already checked similar posts on the forum, but none of these posts is clearly explaining the mathematical part of the backward of multiple forwards.

Thank you,