How are the number of neurons in the output layers chosen?

I discovered that after choosing the number of neurons in the hidden layer, the network automatically sets the number of output neurons. Whats the intuition behind it?

[Osama Tabbakh]

I have the same question but obviously nobody has answer.

[Greg Heath]

???

My answer ( O ) was given ~ 1.5 years ago

Greg

Answer 1

[Greg Heath]

 [ I N ] = size(input)
 [ O N ] = size(target)

 I-H-O  = size of a single layer NN

 You (lucky dog) have the extreme pleasure of either 
 setting H OR accepting the default H=10.

Hope this helps.

Thank you for accepting my exceptional answer

Greg

Answer 2

[Osama Tabbakh]

I discovered why Matlab does that. I will explain it.

Matlab tried to make the samples easier to train, that why he deletes the values of the vector, which are either zero or not important to train. But you get at the end, what you would have.

In the attachment, you see that I have in the output vector 60 components but the last 20 are just zeros, what why he deletes them from the output layer and put it back in the output.