> For the complete documentation index, see [llms.txt](https://wiki.brain4j.org/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://wiki.brain4j.org/readme.md).

# Brain4J

Welcome to the official documentation of **Brain4J**. Here you will find explanations, practical examples, and detailed references covering the core features and design principles of the framework.

### What's Brain4J?

Brain4J is an open-source machine learning framework written entirely in Java, designed for the development, training, and deployment of neural networks with a strong focus on performance, efficiency, and portability.

Unlike traditional machine learning frameworks such as DL4J, PyTorch, or TensorFlow, **Brain4J** does not rely on large external ecosystems or heavyweight native bindings. Its architecture is intentionally minimal, explicit, and close to the underlying math, making behavior predictable and controllable.

### Why choose Brain4J?

* **Pure Java, minimal footprint**: Two <10 MB JARs, almost no external dependencies.
* **Fast by design**: Custom tensor engine with SIMD CPU optimizations and GPU support.
* **Predictable and explicit**: No hidden magic, no opaque graphs, full control over execution.
* **Production-friendly**: Ideal for plugins, lightweight servers, JVM-only and edge environments.
* **More than a toy**: Supports modern models (CNN, RNN, LSTM, Transformers, GCN) and optimizers.

### Start now

<table data-view="cards"><thead><tr><th></th><th></th><th></th><th data-hidden data-card-cover data-type="files"></th><th data-hidden></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><h4><i class="fa-download">:download:</i></h4></td><td><strong>Installation</strong></td><td>Add Brain4J to your next project</td><td></td><td></td><td><a href="/quickstart/installation.md">Installation</a></td></tr><tr><td><h4><i class="fa-play">:play:</i></h4></td><td><strong>Quickstart</strong></td><td>Train and deploy your first model in under 30 seconds</td><td></td><td></td><td><a href="/quickstart/neural-network-example.md">Neural Network Example</a></td></tr><tr><td><h4><i class="fa-sitemap">:sitemap:</i></h4></td><td><strong>Basics</strong></td><td>Understand the foundamentals</td><td></td><td></td><td><a href="/get-started/basics.md">Basics</a></td></tr><tr><td><h4><i class="fa-layer-group">:layer-group:</i></h4></td><td><strong>Tensors</strong></td><td>Understand the basic building unit</td><td></td><td></td><td><a href="/get-started/tensors.md">Tensors</a></td></tr><tr><td><h4><i class="fa-gauge-max">:gauge-max:</i></h4></td><td>GPU</td><td>Discover how to boost performance using the GPU</td><td></td><td></td><td><a href="/get-started/using-the-gpu.md">Using the GPU</a></td></tr><tr><td><h4><i class="fa-notebook">:notebook:</i></h4></td><td>Kotlin Notebooks</td><td>Learn how to use Brain4J in a Jupyter-fashioned way</td><td></td><td></td><td><a href="/get-started/kotlin-notebooks.md">Kotlin Notebooks</a></td></tr></tbody></table>