I usually use gradient descent with Adam optimizer to perform backpropagation in deep learning methods. I knew it is a very efficient method. The question is in which situations we can use "scaled conjugate gradient backpropagation" for optimization in deep learning methods or in artificial neural networks?
Is there any case that using scaled conjugate gradient backpropagation is sufficient? Could you please provide some details when this method can be used and why it should be used?