What operations are performed during testing/prediction of train()?

Let see the example:

%%%Here input x and targets t define a simple function that you can plot:
x = [0 1 2 3 4 5 6 7 8];
t = [0 0.84 0.91 0.14 -0.77 -0.96 -0.28 0.66 0.99];
plot(x,t,'o')

%%%Here feedforwardnet creates a two-layer feed-forward network. The network has one hidden layer with ten neurons.
net = feedforwardnet(10);
net = configure(net,x,t);
y1 = net(x)

How does net work? What are the internal operations?

Answer 1

[Balaji]

Hi Ibrahim,

I understand that you want to understand the 'feedforwardnet' function.

net = feedforwardnet(hiddenSizes,trainFcn)

returns a feedforward neural network with a hidden layer size of hiddenSizes.

For more information on 'feedforwardnet' I suggest you refer to the following link:

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

[K M Ibrahim Khalilullah]

That was not my question, Mainly want to know about implementation. Bty, I have solved. Investigating the internal code. Thanks