(Computer Science / Math / Machine learning) Thanks for your help!

Construct a single hidden layer neural network to solve a non-linear classification task. Each node in your neural network will use the following activation function: f(x) = max(0, x). Additionally, you will use the squared error loss function, defined as the following: K Err(x;, w) = (t* - Ok) where K is the set of nodes in the output layer, to is the correct *=1 value for output node d, and of is the output of node d. Derive the backpropagation weight update rules for this activation function and loss