0
$\begingroup$

For perceptron algorithm, the output and target values are either $0$ or $1$.

Assume output is $y$ and target is $d$.

From http://lcn.epfl.ch/tutorial/english/perceptron/html/learning.html, we can see that the learning / adjustment of the weights are like$$w_j(t+1)=w_j(t)+\eta(d-y)x$$

But if $d$ and $y$ are either $0$ or $1$, then $d-y$ would be either $-1$, $0$ or $1$, then it seems the learning becomes dependent on the learning rate?

$\endgroup$
1
$\begingroup$

True. The learning rate is the size of the steps to move in a direction. the difference between d and y show's the direction to move and Learning rate says how much to move in that direction. Like a Gradient descent.

$\endgroup$
1
$\begingroup$

Learning is dependent on the learning rate.

Imagine you want to drive to some place. The (d-y) is the direction you want to follow, while the learning rate is the speed with which you are going towards it.

$\endgroup$
  • $\begingroup$ $d-y$ is always for the set ${0, 1, -1}$ $\endgroup$ – itdxer May 22 '17 at 11:10
0
$\begingroup$

In the case of the single-layered perceptron that you asked about (which is described in some more detail in wikipedia), the learning doesn't depend on the learning rate.
See here for a short explanation, and here for a longer explanation (including a partial proof and code example).

$\endgroup$

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.