Skip to content
Vol. 1 · Weekly editionWeekly · in your inbox
inklaretaal
Friday, 4 September 2026 · Clarity since 2026
Glossary

What is Neural network?

A neural network is the computing structure many AIs use to recognize patterns, loosely inspired by how brain cells work together.

A neural network is made of layers of small computing points that pass signals to each other. During training the network keeps adjusting those connections, so it gets better at its task. The name echoes the brain, but it is really just math. It is the technique behind image recognition and language models.

What this means for you

You do not need to know the math. It is enough to know this is the building block AI learns with, and that it is not a brain with a mind of its own.

Put precisely

The network only resembles the brain in name. There are no cells in it, just numbers that get nudged a little with every learning step.

Common misconception

That it can explain why it reached an answer. That explanation is not in there; even the people who built it cannot walk through it step by step.


Related words

Machine learningModelTraining

Understand AI, calmly

This word is a start. The inklaretaal Learning curve explains AI step by step in plain language, tuned to your field. The first month is free.

Start free →Back to the glossary