AI Dictionary
Perceptron
Definition
An algorithm for supervised learning of binary classifiers.
Deep Dive
The Perceptron is one of the earliest and simplest algorithms for supervised learning, designed to perform binary classification tasks. Developed by Frank Rosenblatt in 1957, it models a single neuron with multiple inputs, processing them to produce a binary output (typically 0 or 1). Each input is multiplied by a corresponding weight, and these weighted inputs are then summed together. If this sum exceeds a certain threshold (or passes through an activation function), the perceptron outputs one class; otherwise, it outputs the other.
Examples & Use Cases
- 1A simple logic gate (e.g., AND, OR) classifying inputs to true/false
- 2Determining if a customer qualifies for a basic loan based on binary criteria
- 3Classifying emails as "important" or "not important" based on a few keyword presence signals
Related Terms
Neural networkBinary classificationActivation function