Perceptron Model

• The Perceptron is the first neural network model, developed by Frank Rosenblatt in 1958.
• It is a binary classifier used for supervised learning tasks.
• The perceptron is based on the McCulloch & Pitts neuron model combined with the Hebbian learning rule to adjust weights.
• Unlike the fixed-threshold neuron, perceptron can learn the weights and thresholds from training data.

Structure of Perceptron Model:

A perceptron consists of:

1. Inputs (x₁, x₂, …, xₙ)
2. Weights (w₁, w₂, …, wₙ)
3. Bias (b)
4. Net sum calculation
5. Activation function (Step Function)

Mathematical Model: