# How to compute the derivative using chain rule of hidden layer (more than 5 neurons for hidden layer) with bias

In the given problem having 8 inputs with 5 hidden layers and 3 output layers and bias(b1) on hidden layers and bias(b2) on output layer and i have to calculate the no of possible iterations using Back-Propagation algorithm. As this is multi layer network for artificial neural network and solve the non-linear problems.

I am confused in calculating the derivative for the bias (b) and also in the total no of possible iterations for weight update. Please if anyone can help me out. Thanks in advance.

• I can't understand what you are asking. You can do as many iterations of backpropagation and updating the weights as you want. Also, please ask only one question per post. The mathematics on how to do backpropagation and how to compute the partial derivatives / gradients for a neural network are explained in many places. – D.W. Apr 25 at 22:53