MATLAB: Matlab Neural networks: why use sim

sim

After the network has been trained, there seem to be two different ways to utilize the network to make predictions:

(1) test_outputs = net(test_inputs)

(2) test_outputs = sim(net, test_inputs)

What is the difference, and which is better?

Best Answer

The first is newer, so I guess they want you to use it.

I don't know why it was changed.Probably to take some of the load off of sim.

help sim

doc sim

Greg

Related Solutions

MATLAB: Test, train and validation performance are so different from global performance in the neural network

As per my knowledge, the way you are calculating the trainPerformance, valPerformance & testPerformance may not be correct. Instead I would suggest that you can make use of tr.trainInd, tr.valInd & tr.testInd instead of tr.trainMask, tr.valMask & tr.testMask as follows:

trainPerformance = perform(net,t(tr.trainInd),y(tr.trainInd))
valPerformance = perform(net,t(tr.testInd),y(tr.testInd))
testPerformance = perform(net,t(tr.valInd),y(tr.valInd))

Then w.r.t performance function, according to your above code the performance function you are using is 'crossentropy' and hence perform(net,t,y,ew) returns network performance calculated according to the net.performFcn which is 'crossentropy' & not 'mse'.

Also for your additional part, you may have to use

trp = crossentropy(net,t(tr.trainInd),y(tr.trainInd),{1},'regularization',net.performParam.regularization,'normalization',net.performParam.normalization)

and not

trp = mse(net,trainTargets,y)

Refer to the following resources: net.performFcn, crossentropy, Train Neural Network Using mse Performance Function, Analyze Shallow Neural Network Performance After Training, training record & help(net.performFcn) in command window

MATLAB: Help with Monte Carlo sim

format your code by reading this

That code won't even run. Even if it did, your x and y are just rand() which goes between 0 and 1. The y bounds have nothing at all to do with x, x^2 or x^3, but since they all use rand, everything will be between 0 and 1. If you want some higher value, multiply rand() by some amplification factor.

I'm attaching my Monte Carlo demos, for what it's worth.

Best Answer

Related Solutions

MATLAB: Test, train and validation performance are so different from global performance in the neural network

MATLAB: Help with Monte Carlo sim

Related Question