the error appears in defining weightedAdditionLayer

hi, i have defined the weightedAdditionLayer according to the code provided in the help document, but a error'Incorrect number of input arguments for 'backward' in Layer weightedAdditionLayer. Expected to have 5, but instead it has 2.' appears, why?

Answer 1

[Gabija Marsalkaite]

Assuming you have a layer with two inputs (input1 and input2) and one output, 'backward' expects layer, input1, input2, output, dLdz, memory, but if any of them is not used, it can be replaced with ~ e.g. backward(~, ~,~,~,dLdz,~).

This documentation page may help you: https://www.mathworks.com/help/deeplearning/ug/define-custom-deep-learning-layers.html

If that does not solve your problem, could you share your code?