---
title: "Neural network engine in chess"
url: "https://georgelichess.com/glossary/neural-network-engine.md"
canonical_url: "https://georgelichess.com/glossary/neural-network-engine"
last_updated: "2026-11-07"
type: "reference"
summary: "A neural network engine uses a trained neural network to evaluate positions, and NNUE, the efficiently updatable neural network added to Stockfish."
related: ["https://georgelichess.com/glossary/stockfish.md", "https://georgelichess.com/glossary/chess-engine.md", "https://georgelichess.com/glossary/evaluation.md", "https://georgelichess.com/glossary/alpha-beta-pruning.md", "https://georgelichess.com/glossary/search-depth.md", "https://georgelichess.com/glossary/engine-analysis.md", "https://georgelichess.com/glossary/category/computer-chess.md", "https://georgelichess.com/glossary.md"]
---

# Neural network engine in chess

> **For AI agents:** the complete index of GeorgeLiChess pages is [llms.txt](https://georgelichess.com/llms.txt). Every page is also served as markdown at its URL plus .md.

A neural network engine uses a trained neural network to evaluate positions, and NNUE, the efficiently updatable neural network added to Stockfish.

A neural network engine uses a trained neural network to evaluate positions, and NNUE, the efficiently updatable neural network added to Stockfish, combines such an evaluation with fast traditional search.

A neural network [engine](https://georgelichess.com/glossary/chess-engine.md) judges positions using a network that has been trained on very large numbers of positions and results, rather than relying only on hand-written rules about material and structure. The network learns [patterns](https://georgelichess.com/glossary/pattern-recognition.md) that are hard to describe in words, such as how a certain pawn structure and piece placement tend to favor one side.

NNUE stands for efficiently updatable neural network. It is a compact network designed so that when a move changes only a few squares, most of the [calculation](https://georgelichess.com/glossary/calculation.md) can be reused instead of repeated. This makes it fast enough to run on an ordinary processor inside a traditional alpha-beta search. [Stockfish](https://georgelichess.com/glossary/stockfish.md) adopted NNUE and became noticeably stronger as a result, and other engines have used similar ideas. Some other engines are built around larger networks and a different style of search.

For a student, the lesson is that modern [engine evaluations](https://georgelichess.com/glossary/evaluation.md) are a blend of learned judgment and deep calculation. Their verdicts about long-term factors such as space, activity and [king safety](https://georgelichess.com/glossary/king-safety.md) are now often more accurate than before. Still, an engine does not explain itself, so use its answers as a prompt for your own understanding.

Also called: NNUE.

An engine can tell you what "Neural network engine" means for a position, but not which mistakes you keep making; a [first lesson](https://georgelichess.com/book/first-lesson.md) with George Li reviews your games and finds those.

## Related terms

- [Stockfish](https://georgelichess.com/glossary/stockfish.md)
- [Chess engine](https://georgelichess.com/glossary/chess-engine.md)
- [Evaluation](https://georgelichess.com/glossary/evaluation.md)
- [Alpha-beta pruning](https://georgelichess.com/glossary/alpha-beta-pruning.md)
- [Search depth](https://georgelichess.com/glossary/search-depth.md)
- [Engine analysis](https://georgelichess.com/glossary/engine-analysis.md)

## Guides that go further

- [How to choose a chess coach](https://georgelichess.com/how-to-choose-a-chess-coach.md): What to decide first, the questions to ask, what a first lesson should show and the red flags to avoid.
- [How much does chess coaching cost?](https://georgelichess.com/chess-coaching-cost.md): Published rates for private, group and subscription chess coaching, with the source and the date of each.
- [The first lesson](https://georgelichess.com/book/first-lesson.md): A game review, a read on your level and a written study plan from George Li.

[Book your first lesson](https://georgelichess.com/book.md) and George Li reviews your games and builds a study plan around them. Questions about lessons: write to hello@georgelichess.com.

## Related

- [Stockfish in chess](https://georgelichess.com/glossary/stockfish.md)
- [Chess engine](https://georgelichess.com/glossary/chess-engine.md)
- [Evaluation in chess](https://georgelichess.com/glossary/evaluation.md)
- [Alpha-beta pruning in chess](https://georgelichess.com/glossary/alpha-beta-pruning.md)
- [Search depth in chess](https://georgelichess.com/glossary/search-depth.md)
- [Engine analysis in chess](https://georgelichess.com/glossary/engine-analysis.md)
- [Chess terms: Computer chess and analysis](https://georgelichess.com/glossary/category/computer-chess.md)
- [Chess terms glossary: plain definitions](https://georgelichess.com/glossary.md)