---
title: "From Perceptron to Multilayer Network"
description: "A single artificial neuron is a linear score with a threshold, and it cannot separate patterns that are not linearly separable. Stacking layers with a non-linear function between them removes that lim"
canonical: https://lightmysky.com/learn/computing/from-perceptron-to-multilayer-network-mt_TTa7KN1-IO
source: https://lightmysky.com/learn/computing/from-perceptron-to-multilayer-network-mt_TTa7KN1-IO.md
retrieved: 2026-09-12
---

> **Agent view.** This is the Markdown twin of the page, for tools and assistants.
> When to use this site, and the call that answers each job: https://lightmysky.com/agent-instructions.md
> API description (OpenAPI 3.1): https://lightmysky.com/openapi.json · Authentication: https://lightmysky.com/auth.md
> Pricing: https://lightmysky.com/pricing.md · Catalog: https://lightmysky.com/llms.txt · Full catalog: https://lightmysky.com/llms-full.txt
> Every machine-readable file on this domain: https://lightmysky.com/.well-known/ai-catalog.json
> Ask for Markdown with `Accept: text/markdown`, a `.md` address, or `?mode=agent`.

# From Perceptron to Multilayer Network

A single artificial neuron is a linear score with a threshold, and it cannot separate patterns that are not linearly separable. Stacking layers with a non-linear function between them removes that limit, because the middle layers build features of their own.

Subject: Computing · Area: Machine Learning · Ages 21 to 22
Page: https://lightmysky.com/learn/computing/from-perceptron-to-multilayer-network-mt_TTa7KN1-IO

## Ready when they can

- Show that a single unit cannot represent exclusive-or
- Build a two-layer network by hand that does represent it
- Explain why a stack of layers without a non-linearity collapses to one layer

## Lesson: One line is not enough

One artificial neuron takes signals, combines them into a score, and fires past an activation threshold. That draws one straight dividing line, so it can only split patterns a straight line can split.

**Example.** Exclusive-or answers yes in two opposite corners and no in the other two. No single straight line can fence the yes corners together, so one neuron cannot learn it. Give each yes corner its own hidden unit, then let the output fire when either fires.

Stack two layers with a nonlinear step between them and the middle layer builds features of its own. The first layer spots edges, the next combines them into shapes. Without that nonlinear step, the whole stack collapses into one layer.

**Tip.** When someone claims one neuron learned exclusive-or, ask to see the line. Then ask what the hidden layer learned, since that is where the new features live.

**Recap.** One neuron draws one line, exclusive-or needs more, and hidden layers with a nonlinear step build the features that solve it.

## Practice

8 questions on this page, each with its working shown.

## Needs first

- [Logistic Regression and the Decision Boundary](https://lightmysky.com/learn/computing/logistic-regression-and-the-decision-boundary-mt_FaVIaT7xl2)
- [Principal Components and Dimensionality Reduction](https://lightmysky.com/learn/computing/principal-components-and-dimensionality-reduction-mt_l-9XHg_ChZ)

## Opens up

- [Backpropagation: Assigning Blame for an Error](https://lightmysky.com/learn/computing/backpropagation-assigning-blame-for-an-error-mt_5bwaSWfF96)
- [The Transformer Block: Heads, Residuals and Normalisation](https://lightmysky.com/learn/computing/the-transformer-block-heads-residuals-and-normalisation-mt_eKC2IehaDT)