# What is a neural network? > A neural network is a model made of layers of simple math units that learn patterns from examples. It powers chatbots, image reading and voice agents. Source: https://learn.ynteractive.com/content/glossary/neural-network · Updated 2026-10-20 · Free from Stepthrough (https://learn.ynteractive.com) [AI basics](https://learn.ynteractive.com/content/glossary#topic-ai-basics) · [AI glossary](https://learn.ynteractive.com/content/glossary) Quick answer A neural network is a computer model made of many simple math units arranged in layers. Each unit passes numbers to the next, and training adjusts millions or billions of connection strengths until the network turns inputs, like a photo of a receipt, into useful outputs, like the vendor and total. Last updated October 20, 2026 [Take the free module →](https://learn.ynteractive.com/courses/ai-for-accounting-firms/12)Module 12 of the free [AI for Accounting & Bookkeeping Firms](https://learn.ynteractive.com/courses/ai-for-accounting-firms) course, about 12 minutes. No account needed. Updated October 20, 2026 · By [Robert Breen](https://learn.ynteractive.com/content/about) ## Why it matters for a small business Almost every AI tool you use at work runs on a neural network: the chatbot that drafts your email, the tool that reads a scanned invoice, the voice agent that turns speech into text. The name comes from a loose comparison with brain cells, but it is math, not a digital brain. The useful takeaway is how they learn. A neural network is not given rules; it is shown examples and finds patterns. That makes it flexible with messy inputs a rule-based program would reject, and it also means it can be confidently wrong on an input unlike anything it learned from. ## In a real lesson: AI Receipt Extractor: Receipts to Google Sheets with n8n In the [AI Receipt Extractor](https://learn.ynteractive.com/content/ai-receipt-extractor-n8n-google-sheets) lesson, you send a photo, receipt.png, to an n8n AI Agent. The model looks at the image, finds the date, vendor and total, decides it is groceries, and calls the Google Sheets Tool to add a row to the Invoices sheet. Nobody wrote a rule saying where the total sits on a Corner Mart receipt. A neural network learned what receipts look like from many examples, which is why it can read one it has never seen. It is also why the lesson keeps the checking habit: you click the image to compare it with the row before you trust it. [Try this lesson free](https://learn.ynteractive.com/modules/receipt-extractor) or [read the step-by-step guide](https://learn.ynteractive.com/content/ai-receipt-extractor-n8n-google-sheets). ## Common confusions ### Neural network vs algorithm An ordinary algorithm follows steps a person wrote. A neural network's behavior comes from patterns it learned during training. ### Neural network vs AI AI is the broad goal of machines doing tasks that need intelligence. Neural networks are one way to build it, and today the main one. ## Tips - Expect good results on common, clear inputs and test the unusual ones on purpose. - Keep the original next to the AI's output so a person can compare them quickly. - Use plain rules, like an IF node, where a decision must always be exact. ## Related terms [Deep learning](https://learn.ynteractive.com/content/glossary/deep-learning) · [Machine learning](https://learn.ynteractive.com/content/glossary/machine-learning) · [Transformer model](https://learn.ynteractive.com/content/glossary/transformer-model) · [Model parameters](https://learn.ynteractive.com/content/glossary/model-parameters) · [Training data](https://learn.ynteractive.com/content/glossary/training-data) ## More AI basics terms [OCR (optical character recognition)](https://learn.ynteractive.com/content/glossary/ocr) · [Open-weight model](https://learn.ynteractive.com/content/glossary/open-weight-model) · [Overfitting](https://learn.ynteractive.com/content/glossary/overfitting) · [Personally identifiable information (PII)](https://learn.ynteractive.com/content/glossary/pii) ## Where you use it: free lessons - [AI Receipt Extractor: Receipts to Google Sheets with n8n](https://learn.ynteractive.com/content/ai-receipt-extractor-n8n-google-sheets) (n8n, 12 min) - [Your First Voice Agent in ElevenLabs: An After-Hours Receptionist](https://learn.ynteractive.com/content/elevenlabs-voice-agent-tutorial-after-hours-receptionist) (ElevenLabs Agents, 9 min) ## Frequently asked questions **Is a neural network like a human brain?** Only loosely. It borrows the idea of connected units, but it is a large set of numbers and math operations, not a model of how a brain actually works. **Are all AI tools neural networks?** Most modern ones are, including chatbots, image generators and speech-to-text. Some older tools use hand-written rules or simpler statistics. [All AI glossary terms, A to Z](https://learn.ynteractive.com/content/glossary) · [Free prompt templates](https://learn.ynteractive.com/content/prompts)