up vote 2 down vote favorite

I have created a neural network and the performance is good. By using nprtool, we are allow to test the network with an input data and target data. Here is my question, what is the purpose of testing a neural network with target data provided? Isn't it testing should not hav e target data so that we can know how well can the trained neural network perform without target data is given? Hope someone will respond to this, thanks =)

share|improve this question

2 Answers

up vote 0 down vote accepted

I'm not familiar with nprtool, but I suspect it would give the input data to your neural network, and then compare your NN's output data with the target data (and compute some kind of success rate based on that).

So your NN will never see the target data, it's just used to measure the performance.

It's like the "teacher's edition" of the exercise books in school. The student (i.e. the NN) doesn't have the solutions, but her/his answers will be compared against them by the teacher (i.e. nprtool). (Okay, the teacher probably/hopefully knows the subject, but you get the idea.)

share|improve this answer
Ya i get the idea, thanks for the help =) – wan Sep 28 '12 at 4:33
up vote 0 down vote

The "target" data t is the desired y of y=net(x) used as example to train the network. What nprtool do is to divide the training set into three groups: the training set, the validation set and the test set.

The first one is used to actually update the network.

The second one is used to determine the performances of the net (note: this set is NOT used in any way to update the network): as the NN "learns" the error (as difference between the t and net(x)) over the validation set decreases. The trend will eventually stop or even reverse: this phenomena is called "overfitting", which means the NN is now chasing the training set, "memorizing" it at the cost of the ability to generalize (meaning: to perform well with unseen data). So the purpose of this validation set is to determine when to stop the training before the NN starts overfitting. This should answer your question.

Finally third set is for external testing, to leave you a set of data untouched by the training procedure.

share|improve this answer
To clarify: The validation set is generally used to compare the different architectures or parameters of the neural network. For example, while the training set is used to train the network, the validation set would be used to determine how many layers/nodes to have. It can also be used to find a good regularisation parameter. The reason the test set can't be used for this is because the architecture can overfit the validation set, in the same way the learning algorithm can overfit the training set. – J.Ashworth Sep 28 '12 at 0:23
Thanks for the information, it really helps =) – wan Sep 28 '12 at 4:34

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.