1.Previous
3.Next

* , the weight vector
* , the number of inputs
* , some bias
* , the output of the model,

the output is:

:

If we further assume that and , then the output further reduces to:

:

Learning rule

The learning rule used by ADALINE is the LMS ("least mean squares") algorithm, a special case of gradient descent.

Given the following:

* , the learning rate

1.Previous
3.Next