# ReLU.chat

> 6 free learning assistants, 219 explained topics, 6 interactive ML tools and 84 worked-example guides. Chat questions are processed locally in the browser; page and neural model downloads use the network.

## Learn (one page per concept: definition, intuition, example, math)
- [Game theory](https://relu.chat/learn/game-theory/): 80 topics. Strategy, equilibrium and incentives, from the prisoner’s dilemma to mechanism design.
- [Islamic Golden Age](https://relu.chat/learn/golden-age/): 50 topics. Scholars, institutions and ideas of the Islamic Golden Age: algebra, optics, medicine and philosophy.
- [Data science](https://relu.chat/learn/data-science/): 41 topics. Statistics, evaluation and machine-learning concepts with the math shown.
- [Reinforcement learning](https://relu.chat/learn/reinforcement-learning/): 16 topics. Rewards, value functions, bandits, Q-learning and policy gradients.
- [Linear algebra](https://relu.chat/learn/linear-algebra/): 16 topics. Vectors, matrices, eigenvalues and projections: the algebra behind machine learning.
- [Web platform](https://relu.chat/learn/web-platform/): 16 topics. Browser JavaScript, HTTP caching, WebAssembly, workers and local storage.
- [All topics](https://relu.chat/learn/)

## Chat assistants
- [Game Theory Chat](https://relu.chat/chat/game-theory-chat/): On-device NLU assistant for game theory concepts 80 topics.
- [Golden Age Inquiry](https://relu.chat/chat/golden-age-inquiry/): Explore Islamic Golden Age science and philosophy 50 topics.
- [Data Science Chat](https://relu.chat/chat/data-science-chat/): On-device NLU assistant for data science and ML concepts 41 topics.
- [Reinforcement Learning Chat](https://relu.chat/chat/reinforcement-learning-chat/): Learn how agents choose actions: rewards, value functions, bandits, Q-learning, and policy gradients. 16 topics.
- [Linear Algebra Chat](https://relu.chat/chat/linear-algebra-chat/): Build intuition for vectors, matrices, eigenvalues, projections, and the linear algebra behind machine learning. 16 topics.
- [Web Platform Chat](https://relu.chat/chat/web-platform-chat/): Understand browser JavaScript, HTTP caching, WebAssembly, workers, accessibility, and local data storage. 16 topics.

## Interactive tools
- [Neural Network Explorer](https://relu.chat/tools/neural-network/)
- [Activation Functions Explorer](https://relu.chat/tools/activation-functions/)
- [Gradient Descent Lab](https://relu.chat/tools/gradient-descent/)
- [Backpropagation Visualizer](https://relu.chat/tools/backpropagation/)
- [K-Means Clustering Playground](https://relu.chat/tools/k-means-clustering/)
- [Decision Tree Explorer](https://relu.chat/tools/decision-tree/)

## Guides and architecture
- [Learning guides](https://relu.chat/blog/) (84 articles, RSS: https://relu.chat/blog/feed.xml)
- [How it works: architecture and limits](https://relu.chat/how-it-works.html)
- [Policy evaluation](https://relu.chat/data/policy-evaluation.json)
- [Full text for LLMs](https://relu.chat/llms-full.txt)
- [Source code (MIT)](https://github.com/yunusemrejr/relu-chat)

## From the makers
- [How to Remain Valuable When Intelligence Becomes Cheap](https://theknowledgeproject.gumroad.com/l/remainvaluable): a practical book about the human, economic and strategic advantages that stay valuable as AI takes on cognitive work.

These are curated retrieval assistants, not general-purpose language models. They can misunderstand questions and do not execute code or solve arbitrary exercises. Offline use requires previously loaded assets.