Neural Networks: Zero to Hero

Karpathy builds backprop, then GPT, from scratch
Learn AI & machine learningVideo course + codeMITRuns locallyJupyterIntermediate
OSAI Pulse ⓘ ★★★★★★★★★★ /100 signals tracked
🐳 Docker pulls 📦 PyPI downloads / month 📦 npm downloads / month 🚀 Latest release ·
Visit website →View on GitHub

What is Neural Networks: Zero to Hero?

Andrej Karpathy's legendary lecture series: you build automatic differentiation, then a language model, then GPT — writing every line yourself, with nothing hidden.

Why people choose Neural Networks: Zero to Hero

Neural Networks: Zero to Hero at a glance

CategoryLearn AI & machine learning
TypeVideo course + code
LicenseMIT
Runs locallyYes
Built withJupyter
Skill levelIntermediate
Best forthe single best way to truly understand deep learning

Open-source alternatives to Neural Networks: Zero to Hero

Other open-source learn ai & machine learning tools worth comparing:

VirgilioA structured mentor for data science and MLML for BeginnersMicrosoft's classic machine learning courseAI for BeginnersFrom symbolic AI to neural networksGenerative AI for BeginnersBuild generative AI apps, lesson by lessonData Science for BeginnersThe data foundations before any MLLLM CourseThe reference roadmap for learning LLMsLLMs from ScratchBuild a GPT from nothing, line by lineAnnotated Paper Implementations60+ papers implemented and explained side by sideDive into Deep LearningThe textbook where every equation is runnablefastai Book (fastbook)Deep learning for coders, top-downHands-On Machine LearningThe notebooks of the best-selling ML bookHugging Face CourseMaster transformers with the actual libraryHugging Face Agents CourseBuild AI agents, properlyMade With MLFrom notebook to production systemPrompt Engineering GuideThe reference on prompting, backed by papersApplied MLHow real companies actually ship MLML YouTube CoursesThe best free ML courses on YouTube, curatedOpenAI CookbookPractical recipes that work with any OpenAI-compatible APIAwesome Machine LearningThe reference index of ML libraries, by languageAwesome LLMPapers, models and tools of the LLM eraDeep Learning DrizzleUniversity lectures, from the sourceML Interviews BookWhat ML interviews actually ask

Neural Networks: Zero to Hero head-to-head

Neural Networks: Zero to Hero vs VirgilioNeural Networks: Zero to Hero vs ML for BeginnersNeural Networks: Zero to Hero vs AI for BeginnersNeural Networks: Zero to Hero vs Generative AI for BeginnersNeural Networks: Zero to Hero vs Data Science for BeginnersNeural Networks: Zero to Hero vs LLM CourseNeural Networks: Zero to Hero vs LLMs from ScratchNeural Networks: Zero to Hero vs Annotated Paper ImplementationsNeural Networks: Zero to Hero vs Dive into Deep LearningNeural Networks: Zero to Hero vs fastai Book (fastbook)Neural Networks: Zero to Hero vs Hands-On Machine LearningNeural Networks: Zero to Hero vs Hugging Face CourseNeural Networks: Zero to Hero vs Hugging Face Agents CourseNeural Networks: Zero to Hero vs Made With MLNeural Networks: Zero to Hero vs Prompt Engineering GuideNeural Networks: Zero to Hero vs Applied MLNeural Networks: Zero to Hero vs ML YouTube CoursesNeural Networks: Zero to Hero vs OpenAI CookbookNeural Networks: Zero to Hero vs Awesome Machine LearningNeural Networks: Zero to Hero vs Awesome LLMNeural Networks: Zero to Hero vs Deep Learning DrizzleNeural Networks: Zero to Hero vs ML Interviews Book

FAQ

Is Neural Networks: Zero to Hero free?

Neural Networks: Zero to Hero is free and open-source (MIT license), so you can use, self-host and modify it at no cost.

Can I run Neural Networks: Zero to Hero locally?

Yes. Neural Networks: Zero to Hero is designed to run on your own machine or server, keeping your data private.

What is the best alternative to Neural Networks: Zero to Hero?

Popular open-source alternatives include Virgilio, ML for Beginners, AI for Beginners. See the comparisons above to choose.

Explore more open-source AI

Browse the full directory of open-source AI tools, models and projects — updated daily.

Browse all tools →