A Perceptron is the simplest form of a neural network that makes decisions by combining inputs with weights and applying an activation function. It is mainly used for binary classification problems. It forms the basic building block of many deep learning models.

Takes multiple inputs and assigns weights

Computes a weighted sum and applies a threshold

Outputs either 0 or 1 (binary outcome)

Forms the foundation of larger neural networks

The Multilayer Perceptron (MLP)

A multilayer perceptron stacks perceptrons into layers. You have an input layer, one or more hidden layers, and an output layer. Each hidden layer learns increasingly abstract features from the data.

The critical property is that every neuron in one layer connects to every neuron in the next layer — that's why it's called a fully connected or dense network. Each of those connections has its own weight.