0
$\begingroup$

For the simple AND learning with a perceptron, it is required to have two inputs x1 and x2 and one target data y.

enter image description here

Most AND examples (such as in the book "Fundamentals of neural network-fausett") have this network topology in the figure above, that is 2 inputs(x1,x2) and 1 output(o). My question is, how do we give the network the target data (y) if there is only two inputs(x1,x2)??

$\endgroup$
  • $\begingroup$ A 2 input neural net would still have a bias unit. Is this what you are asking? $\endgroup$ – Eric Sep 27 '16 at 19:52
  • 5
    $\begingroup$ The target data is not given to the network. The target data is compared to the output of the network, and the difference (the error signal) is used to train the network. $\endgroup$ – Keith Brodie Sep 27 '16 at 20:17
1
$\begingroup$

The target data is not given to the network. The target data is compared to the output of the network, and the difference (the error signal) is used to train the network.


I've copied Keith Brodie's comment as an answer because the comment is, more or less, an answer to this question. We have a dramatic gap between answers and questions. At least part of the problem is that some questions are answered in comments: if comments which answered the question were answers instead, we would have fewer unanswered questions.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

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