Here in the code the dot sum function is valid for dLdB2 but not for dLdB1. Please tell the reason for it
def loss_gradients(forward_info: Dict[str, ndarray],
weights: Dict[str, ndarray]) -> Dict[str, ndarray]:
”’
Compute the partial derivatives of the loss with respect to each of the parameters in the neural network.
”’
dLdP = -(forward_info[‘y’] – forward_info[‘P’])

I am trying to implement a neural network and train it.
I know my forward function(Forward propagation) works fine. but I am not sure about my backward propagation.
the issue is when I want calculate my sigmoid derivation with sig_derivation function, it encounters overflow.