0
$\begingroup$

I am reading about a Neural Networks project that has some data like this

alt text

I am new to this, and though I think I understand what a 3:1 network mean, I do not understand what number of inputs (to each neuron) means.

alt text

I think this is what a 3:1 network would look like (please correct me if I am wrong). Does 3 inputs per neuron mean that we will have 3 inputs to each of nodes A, B and C? In that case, what would the line connecting A to Z indicate? As in out of three inputs, how is a resultant chosen?

$\endgroup$

closed as off-topic by D.W., Sasho Nikolov, Gamow, Jan Johannsen, Hsien-Chih Chang 張顯之 Feb 19 at 15:12

This question appears to be off-topic. The users who voted to close gave this specific reason:

  • "Your question does not appear to be a research-level question in theoretical computer science. For more information about the scope, please see help center. Your question might be suitable for Computer Science which has a broader scope." – D.W., Sasho Nikolov, Gamow, Jan Johannsen, Hsien-Chih Chang 張顯之
If this question can be reworded to fit the rules in the help center, please edit the question.

7
$\begingroup$

You are bypassing the "hidden layer": A neural network consists of three layers: Input layer, hidden layer, and output layer:

You may also have more than one hidden layer:


(source: mu-sigma.com)

Though, in your case, since the number of hidden layers is not specified, it is safe to assume that there is just 1 hidden layer.

So, for example, in a 3:1 network, you have 1 output neuron, and 3 hidden neurons. The number of inputs shows the number of neurons in the input layer.

$\endgroup$
  • $\begingroup$ thanks, is it compulsory to have a hidden layer in a neural network? $\endgroup$ – Lazer Sep 21 '10 at 5:14
  • $\begingroup$ You are welcome! The hidden layer is not mandatory. Though for an ANN to represent any real-world functionality, hidden layers are usually incorporated. $\endgroup$ – M.S. Dousti Sep 21 '10 at 6:00

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