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.

Technical

KServe and Model Serving on Kubernetes

KServe is a standardized, Kubernetes-native platform for serving machine learning models at scale.

2 min readRead
Technical

Seldon Core and Inference Graphs

Seldon Core is an open-source platform for deploying machine learning models on Kubernetes, with a standout feature: inference graphs.

2 min readRead
Visual AI

IP-Adapter for Image Prompts

IP-Adapter is a lightweight add-on that lets diffusion models like Stable Diffusion accept an image as a prompt, not just text.

2 min readRead
Visual AI

Imagen Text-to-Image

Imagen is Google's text-to-image system that turns written descriptions into photorealistic pictures.

2 min readRead
Visual AI

GLIDE Diffusion Model

GLIDE was an early OpenAI text-to-image diffusion model that showed prompts plus 'classifier-free guidance' could beat earlier GAN-based systems.

2 min readRead
Audio AI

Music Auto-Tagging

Music auto-tagging uses machine learning to listen to a song and automatically attach descriptive labels like genre, mood, instruments, and tempo.

2 min readRead
Audio AI

Musical Timbre Transfer

Timbre transfer reshapes the 'tone color' of audio so one instrument sounds like another, turning a hummed melody into a violin or a trumpet line…

2 min readRead
Audio AI

Acoustic Scene Classification

Acoustic scene classification (ASC) trains machines to recognize the environment a recording was made in, a busy street, a quiet park, a train, a cafe…

2 min readRead
Audio AI

NVIDIA Riva and NeMo Speech

NVIDIA Riva is a GPU-accelerated SDK for production speech AI (ASR, TTS, and translation), while NeMo is the open-source toolkit for training and fine-tuning…

2 min readRead
Audio AI

DeepSpeech Architecture

DeepSpeech is an end-to-end speech recognition model introduced by Baidu in 2014 that maps raw audio features directly to text using a recurrent neural…

2 min readRead
Audio AI

X-Vector Speaker Embeddings

X-vectors are fixed-length numerical fingerprints of a speaker's voice produced by a neural network, used to tell who is speaking regardless of what they say.

2 min readRead
Language AI

Dense Passage Retrieval

Dense Passage Retrieval (DPR) finds relevant text by comparing the meaning of a question and passages as numeric vectors, not matching words.

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.