What Is a Neural Network? A Simple Explanation

"Neural network" is one of those terms everyone hears constantly but rarely sees explained without a wall of math. Here's the plain-English version.

Start with the name

The name comes from a loose analogy to brains: a neural network is built from many simple units ("neurons") connected to each other in layers, similar to how brain cells connect. The analogy is loose — a neural network doesn't work like a real brain — but it explains where the name comes from.

What each "neuron" actually does

Each unit in a neural network does something very simple: it takes in some numbers, multiplies them by adjustable "weights," adds them up, and passes the result to the next layer. That's it. No single unit is smart on its own.

Where the intelligence actually comes from

A neural network usually has an input layer, one or more "hidden" middle layers, and an output layer. Data flows through the layers, getting transformed a little at each step. With enough layers and enough units — modern networks have billions of connections — this simple process can approximate extremely complex patterns: recognizing a face, translating a sentence, predicting the next word in a paragraph.

The "intelligence" isn't in any single unit. It emerges from the combination of millions or billions of simple units working together, each one holding a tiny adjustable piece of the overall pattern.

How the network learns those adjustments

Every connection between units has a weight — a number that determines how much influence that connection has. Training a neural network means repeatedly showing it examples, checking how wrong its output was, and nudging every weight slightly to reduce that error. Repeat this process across a huge dataset, and the weights gradually settle into values that produce useful output.

Why this design became so powerful

Neural networks aren't new — the basic idea dates back decades. What changed recently is scale: far more data, far more computing power, and a specific neural network design called a transformer that's especially good at handling long sequences like sentences and paragraphs. That combination is what produced today's large language models.

Where to go deeper

The AI Glossary has quick definitions for related terms like parameter and transformer. For a full walkthrough of how this connects to how AI actually learns, see How Does AI Actually Work? and the AI Fundamentals course.