I want to train a shallow neural network using known output gradients rather than input/output training pair data

I have a shallow network defined by:

net = fitnet([64,112],'traingd');

The outputs of this network feed INTO a function Y = f(X) where X is the vector of net outputs X=net(I).

I calculate the gradient of Y w.r.t X and want to then train net based on these gradients rather than input/output data for the net.

Answer 1

[arushi]

Hi James,

I understand that you are trying to train a shallow neural network using the known output gradients.

To train a shallow neural network using known output gradients, you can follow these steps:

1. Initialize your shallow neural network with the desired architecture.
2. Define your function Y = f(X) that takes the network outputs X as input and produces the desired output Y. This function represents the relationship between the network outputs and the target outputs.
3. Calculate the gradient of Y with respect to X.
4. Use the calculated gradients to update the network weights using gradient descent or another suitable optimization algorithm.

For additional information, please refer to the following documentation:

https://www.mathworks.com/help/deeplearning/ref/fitnet.html

I hope this helps!