---
title: "Building a Layer"
description: "Run several neurons on one input as a dense layer: one column of weights per neuron, every pre-activation from one matrix product, then a wider layer."
canonical_url: "https://fanout.sh/ai/lessons/neural-network-from-scratch-building-layer"
md_url: "https://fanout.sh/ai/lessons/neural-network-from-scratch-building-layer.md"
access: "pro-preview"
---

# Building a Layer

Run several neurons on one input as a dense layer: one column of weights per neuron, every pre-activation from one matrix product, then a wider layer.

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

## A glimpse of Building a Layer

A dense layer runs several neurons on the same input. Each neuron has its own weights and bias, so the layer can ask several different numerical questions at once.

Take the input [2, −1]. One neuron uses weights [0.5, 1] and bias 0.5. A second uses weights [−1, 2] and bias −0.5. Their weighted sums plus bias, called pre-activation scores, are 0.5 and −4.5.

## 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