Deep Learning A-Z (opens partner site in a new tab)
Intuition-first videos with practical projects. Gentler pacing than fast.ai.
Deep Learning
Neural networks, transformers, and LLMs — understood from the inside.
Follow to see updates in Your Feeds — saved in your browser, no account.
15 picks · 13 free · 14 providers · curated by Rowland Kuru
Editor's intro
Editor's intro
Deep learning powers image recognition, speech, translation, and the large language models everyone now uses. It's also a field where it's easy to run code you don't understand. This feed pairs practical courses that get models training quickly with resources that make you rebuild the core pieces yourself, so the magic becomes mechanism.
Start top-down with fast.ai or bottom-up with Andrew Ng's specialization — both work; pick the one that matches how you like to learn. Then do Karpathy's Zero to Hero, which is the single best way to understand how an LLM actually works. The advanced section holds Stanford's flagship courses and the textbooks specialists keep coming back to.
Start here
Practical Deep Learning for Coders
Practical Deep Learning for Coders by fast.ai has you training a state-of-the-art image classifier in the first lesson, then spends the rest of the course explaining why it works. That top-down approach suits people who learn by doing, and Jeremy Howard is candid about which details matter and which are academic. It's free, uses PyTorch, and the accompanying book is free online too. You need a year or so of Python; you don't need a maths degree.
This week added
Lil'Log (opens provider site in a new tab)
Long, carefully referenced surveys of attention, diffusion, and agents. Better than most review papers.
All picks
Partner Some links on this page are affiliate links, marked Partner. Commissions fund the site at no cost to you. Read our affiliate disclosure.
Beginner · 4
Train your first neural networks and build intuition for what they learn. Python is required; heavy math isn't yet.
CS50's Introduction to Artificial Intelligence with Python (opens provider site in a new tab)
Search, optimization, and neural networks in Python. A rigorous tour before specializing.
Free Certificate optional
Neural Networks (3Blue1Brown) (opens provider site in a new tab)
Visual intuition for backpropagation, transformers, and attention. Watch before starting any course.
Free
PyTorch Tutorials (opens provider site in a new tab)
Official, runnable tutorials. Start with "Learn the Basics" before any third-party course.
Free
Deep Learning A-Z (opens partner site in a new tab)
Intuition-first videos with practical projects. Gentler pacing than fast.ai.
Paid 30-day refund Partner New
Intermediate · 5
Build networks and transformers from scratch, and work with the libraries used in real projects.
DeepLearning.AI courses (opens provider site in a new tab)
Short courses on current tools like RAG and agents, often taught with the toolmakers.
Free
Dive into Deep Learning (opens provider site in a new tab)
An interactive textbook with runnable code. Theory and practice on the same page.
Free Free to read online
Hugging Face LLM Course (opens provider site in a new tab)
Transformers, fine-tuning, and datasets with the library everyone uses. Free and practical.
Free
Neural Networks: Zero to Hero (opens provider site in a new tab)
Build backprop, then a GPT, from scratch. The best way to really understand LLMs.
Free
Deep Learning Specialization (opens partner site in a new tab)
Andrew Ng's bottom-up counterpart to fast.ai. Clear on the math behind each architecture.
Paid Financial aid available Partner
Advanced · 5
University-level courses and textbooks for vision, language, and modern architectures.
CS224N: Natural Language Processing with Deep Learning (opens provider site in a new tab)
The standard NLP course, now centered on transformers and LLMs. Lectures are free online.
Free
CS231n: Deep Learning for Computer Vision (opens provider site in a new tab)
Stanford's legendary vision course. The assignments make you implement everything yourself.
Free
Deep Learning (Goodfellow, Bengio, Courville) (opens provider site in a new tab)
The foundational textbook. Parts are dated, but its math chapters remain a reference.
Free Free to read online
Lil'Log (opens provider site in a new tab)
Long, carefully referenced surveys of attention, diffusion, and agents. Better than most review papers.
Free New
Understanding Deep Learning (Simon Prince) (opens provider site in a new tab)
The modern textbook: clear figures, current architectures, and free. Our pick over older references.
Free Free PDF