Perceptron
The simplest form of an artificial neural network, consisting of a single layer that outputs a binary decision based on a linear combination of inputs.
Think of It Like This
Like a strict bouncer who multiplies your age, height, and attire by specific weights, and only lets you in if the total score beats a threshold.
Invented in the 1950s, the perceptron learns a linear decision boundary by updating its weights when it makes an incorrect prediction. However, it is fundamentally limited to solving linearly separable problems. It famously cannot learn the XOR function without being expanded into a Multi-Layer Perceptron (MLP) with hidden layers.