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.

Industries

AI in Weather Forecasting

AI weather models learn atmospheric patterns directly from decades of past observations, producing 10-day forecasts in seconds that rival or beat…

2 min readRead
Industries

AI in Predictive Maintenance

Predictive maintenance uses sensor data and machine learning to forecast when a machine will fail, so it can be fixed just before breaking rather…

2 min readRead
Technical

Reranking Models

A reranker is a second-stage model that re-scores a shortlist of search results for relevance to a query, sharpening the ordering after a fast retriever…

2 min readRead
Language AI

Masked Language Modeling

Masked language modeling teaches an AI to fill in deliberately hidden words using the full surrounding context, both left and right.

2 min readRead
Language AI

Next-Token Prediction

Next-token prediction is the deceptively simple objective behind GPT-style models: given everything so far, guess the next chunk of text.

2 min readRead
Language AI

Sequence-to-Sequence Models

Sequence-to-sequence models map one sequence to another of possibly different length, like translating a sentence or summarizing a document.

2 min readRead
Technical

Model Drift Detection

Model drift detection is the practice of monitoring a deployed machine learning model to catch when its accuracy quietly degrades because the real world has…

2 min readRead
Technical

A/B Testing for ML Models

A/B testing for ML models means routing live traffic to two model versions at once and measuring which one actually performs better on real users and real…

2 min readRead
Technical

Model Serialization Formats

Model serialization is how a trained machine learning model gets saved to disk so it can be loaded and run later, on a different machine or in a different…

2 min readRead
Visual AI

Image Super-Resolution

Image super-resolution uses AI to turn low-resolution, blurry images into sharp, high-resolution ones by intelligently inventing plausible detail.

2 min readRead
Visual AI

Flow Matching

Flow matching is a newer way to train generative models that learns a smooth 'velocity field' carrying random noise straight to realistic data.

2 min readRead
Visual AI

Consistency Models

Consistency models are generative models that learn to jump from noise to a clean image in a single step (or just a few), instead of the dozens of steps…

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.