Free AI library

Learn AI.Free forever.

1019 plain-English guides, structured learning paths, and an open library — built by an independent 501(c)(3) nonprofit so anyone can understand modern AI.

1019Free guides
9Topic tracks
~2 minPer guide
~34hReading time

Start here

Five outcome-based courses

Each course includes explicit outcomes, mapped competencies, practice activities, and an applied capstone.

Topic tracks

Browse by track

Jump into the area you care about. Every track has multiple plain-English guides.

Full library

All guides

1019 of 1019 guides shown. Filter by track or search above.

Audio AI

Wav2Letter Convolutional ASR

Wav2Letter is an end-to-end speech recognition system from Facebook AI that used only convolutional neural networks, no recurrence.

2 min readRead
Audio AI

Jasper and QuartzNet ASR

Jasper and QuartzNet are NVIDIA's end-to-end convolutional speech recognition models, with QuartzNet being a dramatically smaller, efficient redesign…

2 min readRead
Language AI

Perplexity and Language Metrics

Perplexity is the classic score for how 'surprised' a language model is by real text — lower means it predicts words more confidently.

2 min readRead
Language AI

LoRA and Parameter-Efficient Tuning

LoRA lets you customize a giant pretrained model by training only a tiny set of new weights instead of all billions.

2 min readRead
Society

Prompt Injection Attacks

Prompt injection is when hidden or malicious instructions hijack an AI system into ignoring its rules and doing the attacker's bidding.

2 min readRead
Language AI

Constitutional AI

Constitutional AI is Anthropic's method for aligning models using a written set of principles — a 'constitution' — so the AI critiques and revises its own…

2 min readRead
Visual AI

Vision Transformers

Vision Transformers (ViTs) apply the transformer architecture that powers ChatGPT to images, treating a picture as a sequence of patches instead of a grid…

2 min readRead
Visual AI

Stable Diffusion

Stable Diffusion is an open-source text-to-image model, released by Stability AI in 2022, that generates pictures by gradually removing noise from a random…

2 min readRead
Visual AI

Midjourney

Midjourney is a popular commercial text-to-image service known for its striking, highly aesthetic results and its origins as a Discord bot.

2 min readRead
Fundamentals

Overfitting and Underfitting

Overfitting is when a model memorizes its training data and fails on new examples; underfitting is when it is too simple to capture the real pattern.

2 min readRead
Fundamentals

Regularization

Regularization is a set of techniques that deliberately constrain a model so it generalizes to new data instead of memorizing the training set.

2 min readRead
Technical

Batch Normalization

Batch normalization is a technique that rescales the inputs to each layer of a neural network during training, making deep networks train faster and more…

2 min readRead

Finished reading? Prove it.

Check what you learned with topic quizzes, then explore our structured courses and current certification requirements. Core guides remain free to read.