---
title: "Implementing a Network"
description: "Connect two layers so the numbers one layer produces feed the next. Trace two examples through two hidden units and one output, then add a loss."
canonical_url: "https://fanout.sh/ai/lessons/neural-network-from-scratch-implementing-network"
md_url: "https://fanout.sh/ai/lessons/neural-network-from-scratch-implementing-network.md"
access: "pro-preview"
---

# Implementing a Network

Connect two layers so the numbers one layer produces feed the next. Trace two examples through two hidden units and one output, then add a loss.

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

## A glimpse of Implementing a Network

A neural network connects layers: the numbers produced by one become the inputs to another. We can understand that connection by following two examples through a network with two hidden units and one output.

“Hidden” just means the intermediate values are inside the model rather than its final answer.

## 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