Perceptron Algorithm in Machine Learning

number of iterations

1

2

3

4

5

6

This Demonstration illustrates the perceptron algorithm with a toy model. The perceptron algorithm is used in machine learning to classify inputs and decide whether or not they belong to a specific class.

In this Demonstration, a training dataset is generated by drawing a black line through two randomly chosen points. This line is used to assign labels to the points on each side of the line into red or blue. Then, the perceptron learning algorithm is used to update the weights and classify this data with each iteration, as shown on the right. The updated weights are displayed, and the corresponding classifier is shown in green. The points that are classified correctly are colored blue or red while the points that are misclassified are colored brown.

References

[1] Wikipedia. "Perceptron." (May 16, 2018) en.wikipedia.org/wiki/Perceptron.

[2] Wikipedia. "Linear Classifier." (May 16, 2018) en.wikipedia.org/wiki/Linear_classifier.

Permanent Citation

Arnab Kar

"Perceptron Algorithm in Machine Learning"
http://demonstrations.wolfram.com/PerceptronAlgorithmInMachineLearning/
Wolfram Demonstrations Project
Published: May 17, 2018