How is backpropagation implemented in siamese networks

[Ritu_Pande]

I am confused about how back propagation is implemented in Siamese networks if the sister networks share the same weights. How are these common weights updated based on the loss calculated i.e. in what sequence will the weights be updated , to adjust the contribution of different paths?

Can someone explain or provide a reference where I can read about it?

[gent.spah]

You can check this post, or other similar if you search:

Multi Output Regression: Multi Parameters?

Hi @Pere_Martra I saw this post and this is what I think about it in a previous post. Basically you have one set of weights for the main branch and 2 othes sets for each branch when it splits. How this is done, I always take a water flow in pipes analogy, one main branch splits in 2 other branches, the pressure is the same in the main branch but is different in splits (here the pressure can be anlogue to gradients/learned weights). The overall presure in each part of the systems is decided…