Neural Networks: Zero to Hero vs 
Applied ML
Neural Networks: Zero to Hero vs Applied ML compared for 2026 — features, license, ease of use, performance and which one to choose. Karpathy builds backprop, then GPT, from scratch vs How real companies actually ship ML.
Updated regularly · curated by OpenSourceAI.tech
Neural Networks: Zero to Hero vs Applied ML at a glance
| Spec | Neural Networks: Zero to Hero | Applied ML |
|---|---|---|
| Category | Learn AI & machine learning | Learn AI & machine learning |
| Type | Video course + code | Curated papers & posts |
| License | MIT | MIT |
| Runs locally | Yes | Yes |
| Primary language | Jupyter | Markdown |
| Ease of use | Intermediate | Intermediate |
| Best for | the single best way to truly understand deep learning | learning from what companies really did |
| GitHub stars | — | 29.9k |
How Neural Networks: Zero to Hero and Applied ML score
| Criterion | Neural Networks: Zero to Hero | Applied ML |
|---|---|---|
| Popularity | n/a | 3.5 |
| Maintenance | n/a | 2.0 |
| Ease of use | 3.5 | 3.5 |
| Privacy | 5.0 | 5.0 |
| License freedom | 5.0 | 5.0 |
Scores are computed automatically from public signals — GitHub stars (popularity), recent commit activity (maintenance), license type (freedom), local-first design (privacy) and onboarding complexity (ease of use). Indicative, not a verdict.
What each one 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.
- Widely considered the best deep learning teaching ever made
- You implement backpropagation yourself — it finally clicks
- Ends with a working GPT you wrote line by line
Applied ML
Eugene Yan's curated collection of papers and engineering blog posts on how companies actually build and deploy ML systems in production — organised by problem, not by algorithm.
- Real production systems, not toy examples
- Organised by problem, not by algorithm
- Curated by a practising ML engineer
Key differences
Neural Networks: Zero to Hero is video course + code, while Applied ML is curated papers & posts. In short, Neural Networks: Zero to Hero fits the single best way to truly understand deep learning, and Applied ML fits learning from what companies really did.
Which should you choose?
Choose Neural Networks: Zero to Hero for the single best way to truly understand deep learning. Choose Applied ML for learning from what companies really did.
There is rarely one winner — many setups use both. The right pick depends on your hardware, your team's skills, and whether you value simplicity or control.
Frequently asked questions
Is Neural Networks: Zero to Hero or Applied ML easier to use?
Both sit at a similar level (Intermediate). Your choice should come down to fit rather than difficulty.
Are Neural Networks: Zero to Hero and Applied ML free?
Neural Networks: Zero to Hero is free and open source (MIT), and Applied ML is free and open source (MIT). Neither charges for the core software.
Can I run Neural Networks: Zero to Hero and Applied ML locally?
Neural Networks: Zero to Hero: yes · Applied ML: yes. Both can be used without sending your data to a third-party cloud where their setup allows.
Neural Networks: Zero to Hero vs Applied ML — which should I pick in 2026?
Choose Neural Networks: Zero to Hero for the single best way to truly understand deep learning. Choose Applied ML for learning from what companies really did.
People also compare
Explore more open-source AI
Browse thousands of open-source AI tools, models and projects — all curated in one place, updated daily.
Explore the directory →