# Multilayer Perceptron: What is the value used to update the weights in the hidden layers?

As i understand for the output layer the error rate is used with the mean squared error function to update the weights. For the hidden layers as well? Does that make sense?

• Note that mean squared error is just one example of a function that can be used to as a loss function. For classification tasks, typically the negative log likelihood is used. – timleathart Oct 14 '19 at 23:38