Explore modules

Perceptron

Visualize the Perceptron algorithm learning a linear decision boundary.

Free theory article

Visualize the Perceptron algorithm learning a linear decision boundary.

Concept & interpretation

The Perceptron is one of the oldest and simplest machine learning algorithms. Invented by Frank Rosenblatt in 1957, it is a binary linear classification algorithm. The Perceptron models a biological neuron by taking a set of input values, multiplying each by a corresponding weight, summing them up, and passing the result through an activation function (often a step function) to determine the output class. If the data is linearly separable, the Perceptron algorithm is guaranteed to converge to a solution.

Read the full free theory article