fast.aiCurated
fast.ai
Practical Deep Learning for Coders (fast.ai)
For: Engineers who learn by doing, not by deriving
Intermediate · ~70 hours (8 lessons + projects) · Free
Practical Deep Learning for Coders (fast.ai)vsNeural Networks: Zero to Hero (Andrej Karpathy)
Side-by-side comparison on level, duration, pricing, instructor, tier. Editor verdict on which course wins for which buyer.
fast.ai
fast.ai
Practical Deep Learning for Coders (fast.ai)
The defining contrarian course in ML education. fast.ai's top-down philosophy — train a working image classifier in lesson 1, understand the math by lesson 6 — works for some learners and frustrates others. We recommend it for engineers who learn by doing rather than by first principles. The course extends to LLMs in later lessons (Jeremy regularly updates), and the companion book ('Deep Learning for Coders with fastai and PyTorch') is genuinely the best paper book on practical deep learning. Free; the only cost is the 70-hour commitment. If Karpathy's Zero-to-Hero is too math-heavy, this is the alternative.
▶
YouTube
Neural Networks: Zero to Hero (Andrej Karpathy)
The single most-recommended free resource in modern AI education. Karpathy builds a working autograd engine, then a character-level language model, then a tokenizer, then a working GPT — all from scratch in PyTorch, explaining every line. The 'Let's build GPT' and 'Let's build the GPT Tokenizer' lectures specifically have become canonical references — every senior AI engineer has watched them. The catch: it's 25 hours of dense math-and-code video. You won't follow if you can't keep up with Python + linear algebra. But if you can, no paid course delivers comparable depth.
Side-by-side
| Dimension | Practical Deep Learning for Coders (fast.ai) | Neural Networks: Zero to Hero (Andrej Karpathy) |
|---|---|---|
| Provider | fast.ai | YouTube |
| Editorial tier | Curated | Hands-on reviewed |
| Level | Intermediate | Advanced |
| Format | self paced | video |
| Duration | ~70 hours (8 lessons + projects) | ~25 hours (11 lectures) |
| Pricing | Free | Free |
| Instructor | Jeremy Howard & Sylvain Gugger — Founder fast.ai; Hugging Face research engineer | Andrej Karpathy — Co-founder OpenAI; former Director of AI at Tesla |
| Rating | No public rating | No public rating |
| Topics | llm fundamentals, fine tuning, computer vision | llm fundamentals, fine tuning, ai engineering |
| Last verified | 2026-05-23 | 2026-05-23 |
Pros & cons
Practical Deep Learning for Coders (fast.ai)
Pros
- +Top-down pedagogy — you ship working models from lesson 1
- +Free, regularly updated, by one of the most respected practitioners in the field
- +Excellent companion book if you prefer paper
Cons
- −70 hours is a real ask
- −Pedagogy is contrarian — some learners want first principles, not top-down
- −Less LLM-focused than the field demands in 2026; deep-learning generalist
Neural Networks: Zero to Hero (Andrej Karpathy)
Pros
- +By a co-founder of OpenAI — no higher-authority instructor exists
- +Free, on YouTube, with companion GitHub code
- +The "Let's build GPT from scratch" lecture is the single most-cited free resource in AI education
Cons
- −25-hour commitment of dense material — you have to actually do the exercises
- −Pre-reqs are real: comfortable Python + undergrad linear algebra
- −No certificate, no community — pure self-direction
Which course is for whom?
Practical Deep Learning for Coders (fast.ai)
Best for
- · Engineers who learn by doing, not by deriving
- · People who tried Karpathy's course and bounced off the math density
Not ideal for
- · Anyone needing LLM-specific depth — this is broader deep learning
- · Time-constrained learners — there are shorter paths
Neural Networks: Zero to Hero (Andrej Karpathy)
Best for
- · Engineers who plan to train, fine-tune, or research LLMs at depth
- · Anyone tired of "wrapper" courses who wants to understand transformers from first principles
Not ideal for
- · Casual learners — the dropout rate on the lecture series is high for a reason
- · Anyone wanting application patterns (LangChain, prompt engineering) — wrong course
Editor's short verdict
Take Neural Networks: Zero to Hero (Andrej Karpathy) first if you're new to the topic; once you have the basics, Practical Deep Learning for Coders (fast.ai) is the natural next step. They're complementary in a learning path, not directly competing.
▶Hands-on reviewedEditor's pick
YouTube
Neural Networks: Zero to Hero (Andrej Karpathy)
For: Engineers who plan to train, fine-tune, or research LLMs at depth
Advanced · ~25 hours (11 lectures) · Free
Other comparisons
Similar courses you might also be considering.
- Compare Practical Deep Learning for Coders (fast.ai) vs AWS Generative AI Learning Plan →
- Compare Practical Deep Learning for Coders (fast.ai) vs Hugging Face LLM Course →
- Compare Practical Deep Learning for Coders (fast.ai) vs Generative AI with Large Language Models →
- Compare Neural Networks: Zero to Hero (Andrej Karpathy) vs Hugging Face LLM Course →
- Compare Neural Networks: Zero to Hero (Andrej Karpathy) vs AWS Generative AI Learning Plan →
- Compare Neural Networks: Zero to Hero (Andrej Karpathy) vs Google Cloud Generative AI Learning Path →