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.

Language AI

BM25 and Lexical Retrieval

BM25 is the classic keyword-based ranking function that scores documents by how often query terms appear, adjusted for term rarity and document length.

2 min readRead
Language AI

HyDE Hypothetical Document Embeddings

HyDE improves retrieval by first asking a language model to imagine a fake answer document, then searching with that document's embedding instead of the raw…

2 min readRead
Applications

AI in Voice Biometrics Authentication

Voice biometrics uses AI to verify your identity from the unique acoustic and behavioral patterns in your speech.

2 min readRead
Applications

AI in Subtitling and Closed Captioning

AI turns spoken audio into synchronized on-screen text, automating subtitles for translation and closed captions for accessibility.

2 min readRead
Applications

AI in Patent Search and Analysis

AI helps inventors, lawyers, and examiners search millions of patents and analyze them by meaning rather than just keywords.

2 min readRead
Language AI

Speculative Decoding Draft Models

Speculative decoding uses a small, fast 'draft' model to guess several upcoming tokens that a large model then verifies in one pass.

2 min readRead
Language AI

Lookahead Decoding

Lookahead decoding speeds up LLM generation without any extra draft model by guessing and verifying multiple future tokens in parallel using n-grams…

2 min readRead
Language AI

ColBERT Late Interaction Retrieval

ColBERT is a retrieval model that represents each query and document as many token-level vectors and scores them with a fine-grained 'late interaction' step.

2 min readRead
Technical

Vanishing and Exploding Gradients

When training deep networks, error signals shrink toward zero or blow up toward infinity as they travel backward through many layers.

2 min readRead
Technical

Gradient Clipping

A simple, widely used safeguard that caps how large gradient updates can get during training.

2 min readRead
Technical

Weight Initialization

How you set a neural network's starting weights before training begins, which strongly shapes whether signals and gradients stay healthy through deep layers.

2 min readRead
Visual AI

Perceptual Loss and LPIPS

Perceptual loss measures how similar two images look to humans by comparing deep neural network features instead of raw pixels.

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.