Question

Consider a classification problem with two classes as C1 and C2. There are two numerical input variables X1 and X2, taking values between 0 and infinity. All observations are of class C1, if they are above X2 = 1/X1 curve (a hyperbola) All other observations are class C2.

Describe how multilayer perceptrons can separate such a boundary using as few hidden nodes as possible.

Answer 1

"A multilayer perception is a class of feed forward neural network.

It has three layers of nodes.

One is an input node and the other nodes use a non linear activation function.

From the question ,it is clear that the observations are of class C1, if they are above X2=1/X1.

Multilayer perceptrons sometimes have a single hidden layer.When they have such a layer, it is said to be "vanillla neural networks."

The MLP consists of three or more layers of nonlinearly-activating nodes making it a deep neural network.

In this way, multilayer perceptrons can separate a boundary.