# Recurrent Neural Network (RNN)

> A network that reads in order. It keeps a short memory of what came before.

**Field:** Artificial Intelligence  
**Category:** Machine Learning  
**Also known as:** RNN

## Think of it like

Think of it like reading a story one word at a time. You keep the plot in mind as you go.

## Definition

A recurrent neural network reads data in order, one piece at a time. After each piece, it keeps a small memory and passes it to the next step. This lets it use what came before, such as the earlier words in a sentence. It was widely used for speech and text. Its memory fades over long stretches, and later designs tried to fix that.

## Example

Jack's phone keyboard guesses his next word. An RNN reads 'see you' and, with that in memory, offers 'tomorrow'.

## Why it matters

It was the main tool for language and speech for years. Today transformers do most of that work.

## Common mistake

Expecting it to remember a whole page. Its memory fades, so it often loses track of words from long ago.

## Three principles

- **In order.** One piece after another.
- **Carries memory.** From each step to the next.
- **Memory fades.** Long stretches are hard.

## Related terms

- [Long Short-Term Memory (LSTM)](https://learn.benibix.com/term/ai/long-short-term-memory)
- [Convolutional Neural Network (CNN)](https://learn.benibix.com/term/ai/convolutional-neural-network)
- [Neural Network](https://learn.benibix.com/term/ai/neural-network)
- [Deep Learning](https://learn.benibix.com/term/ai/deep-learning)
- [Natural Language Processing (NLP)](https://learn.benibix.com/term/ai/natural-language-processing)

## Taught in

- [CNNs, RNNs and LSTMs](https://learn.benibix.com/learn/ai-machine-learning/cnns-rnns-and-lstms): Machine Learning, 15/18

![Four boxes in a row, one per word. Each box reads a word from below and passes a memory arrow to the next box. In the LSTM version, each box has gates marked keep and forget.](https://learn.benibix.com/diagrams/nn-rnn.svg)

---

Source: https://learn.benibix.com/term/ai/recurrent-neural-network
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-17
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
