How to calculate gradient of output of a neural network with respect to its parameters?

utkarsh_singh_021 - 2021-05-04T15:31:49+00:00

Question: How to calculate gradient of output of a neural network with respect to its parameters?

I am new to the Deep Learning toolbox. I am working on a Reinforcement Learning problem wherein I need to calculate the derivative of the output of NN with respect to parameters.   More specifically, let the I/O relation of the neural network be defined as , where x is the input, y is the output, and θ contains the weights and biases of the neural network. For a specific input , I am interested in calculating . Any idea how I should go about this with the deep learning toolbox?

Related Questions

Expert Answer

Neeta Dsouza answered . 2025-11-20

function y = f(x,theta)
y = sum(sin(theta(1)*x+theta(2)));
end

function [y, dy] = fun_and_deriv(x,theta)
y = f(x,theta);
dy = dlgradient(y,theta);
end

x = dlarray(0:10);
theta = dlarray([1 2]);
[y, dy] = dlfeval(@fun_and_deriv,x,theta)

y = 
  1×1 dlarray

   -0.9668

dy = 
  1×2 dlarray

    0.6788   -1.1095

 

Not satisfied with the answer ?? ASK NOW