...

/

Introduction to Perceptron

Introduction to Perceptron

Learn what a perceptron is and the types of boundaries it can make.

What is a perceptron?

Perceptron is a binary linear classifier used in supervised learning to classify the given input data.

Visualize a perceptron

In the case of two input data points, the perceptron model makes a line that separates the two classes.

Boundary

The boundary line that separates the two classes are:

w1x1+w2x2+b=0w_1x_1 + w_2x_2 + b = 0

Here:

  • x1x_1 and x2x_2 are the inputs
  • w1w_1 and w2w_2 are the weights
  • bb is the bias

Prediction

The predicted value on applying the step function is given by:

y^\hat{y}={\Bigg\{ 1if  w1x1+w2x2+b>=00otherwise\begin{matrix} 1 & {if\; w_1x_1 +w_2x_2 + b >= 0}\\ \\ 0 & otherwise \end{matrix}

Quiz

1

A perceptron model draws a line between passed and failed students including the student mark on the two tests. Suppose the equation for the line is: (4x1+5x25=04x_1 + 5x_2 - 5 = 0)

What is the score of the student who got 2 in question 1 and 3 in question 2?

A)

18

B)

23

Question 1 of 30 attempted

In the case of three input data points, the perceptron model would separate the two classes using a plane:

Boundary

The plane separating the data points would be:

...