---
title: "Single Neuron From Scratch"
description: "Build one artificial neuron by hand: weight each input, add a bias, apply ReLU, and run it in Python on [2, −1]. Then see what learning would change."
canonical_url: "https://fanout.sh/ai/lessons/neural-network-from-scratch-single-neuron"
md_url: "https://fanout.sh/ai/lessons/neural-network-from-scratch-single-neuron.md"
access: "pro-preview"
---

# Single Neuron From Scratch

Build one artificial neuron by hand: weight each input, add a bias, apply ReLU, and run it in Python on [2, −1]. Then see what learning would change.

- Access: Fanout Pro (public preview)
- Module: Neural Network from Scratch

## A glimpse of Single Neuron From Scratch

A small artificial neuron takes several numbers and produces one number. It multiplies each input by a weight, adds the results and a bias, then applies an output rule.

Use two inputs, [2, −1], and weights [0.5, 1]. The weights decide how each input contributes. A bias of 0.5 adds the same offset regardless of the input.

## Continue learning

Pro unlocks guided learning, complete notes, practical walkthroughs, exercises, and every AI Research lesson.

---
This representation contains public Fanout content only. Protected Pro lessons, account data, billing, checkout, and pricing are not included.

Browse the public content map: https://fanout.sh/sitemap.md