0
$\begingroup$

In this page it's told:

In Single Perceptron / Multi-layer Perceptron(MLP), we only have linear separability because they are composed of input and output layers(some hidden layers in MLP)

What does it mean? I thought the MLP was a non-linear classifier. Could you explain it to me?

$\endgroup$
1
$\begingroup$

In Single Perceptron / Multi-layer Perceptron(MLP), we only have linear separability because they are composed of input and output layers(some hidden layers in MLP)

This is wrong.

A multi-layer perceptron (i.e. a feed-forward neural network) with non-linear activation functions can perform non-linear classification and regression. In fact, an MLP with one hidden layer with an arbitrary number of hidden nodes, each of them with a sigmoid (which is a non-linear function), can approximate any continuous function (up to an approximation error).

On the other hand, perceptrons can't do that. They perform only linear classification/regression.

I thought the MLP was a non-linear classifier.

You're right, unless the MLP only uses linear activation functions. In that case, it won't be able to perform non-linear classification/regression.

(P.S.: I suggest you always question the truth and correctness of what you read on the web, especially, on sites like Medium, as you actually did!)

$\endgroup$
4
  • $\begingroup$ Is it true to say that, in a MLP the neurons in the hidden layer can use only nonlinear activation functions while the neurons in the output layer can use or a linear or a non linear activation function ? $\endgroup$ – AleWolf Apr 23 '20 at 10:45
  • $\begingroup$ @AleWolf They can use linear or non-linear activation functions everywhere, in principle. $\endgroup$ – nbro Apr 23 '20 at 11:18
  • $\begingroup$ But, if they use linear activation function everywhere then that particular MLP would be linear, right ? $\endgroup$ – AleWolf Apr 23 '20 at 11:49
  • $\begingroup$ @AleWolf It would be linear in the sense that it would represent a straight-line. $\endgroup$ – nbro Apr 23 '20 at 11:56

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.