How to compute gradients using the Neural Network Toolbox software?

I've been reading Neural_Network_Toolbox_Users_Guide and I have a question about below section.

As what it said in 3-19,

In fact, the gradients and Jacobians for any network that has differentiable transfer functions, weight functions and net input functions can be computed using the Neural Network Toolbox software through a backpropagation process. You can even create your own custom networks and then train them using any of the training functions in the table above. The gradients and Jacobians will be automatically computed for you.

Could you explain this part in detail how we can only get the gradient of training functions?

Answer 1

[Greg Heath]

help gradient

doc gradient

Thank you for formally accepting my answer

Greg

[Howard Lam]

Gradient function computes only the numerical gradient which is just really the difference.

I am not sure if the activation functions in the neural network toolbox is symbolic.