Neural Networks (video series) review
3Blue1Brown · youtube
Grant Sanderson's animated series on how neural networks, backpropagation and transformers work.
What does it take?
| Difficulty | 2 out of 5 |
|---|---|
| Hours | Not checked yet |
| Format | Video |
| Maths needed | University-level maths |
| Coding needed | No code |
| Hardware needed | Not checked yet |
| Certificate | No certificate |
| Free to audit | Yes |
| Pace | Self-paced |
| Last updated by the provider | Not checked yet |
Who should take it, and who should skip it?
Take it if you are
- Visual learners
- Anyone about to start a deep learning course
- Non-coders who like maths
Skip it if you are
- People who need a certificate
- Anyone who wants hands-on exercises
What will you be able to do after it?
- Picture what a neural network is doing
- Explain gradient descent and backpropagation
- Understand the attention mechanism in transformers
What's in each module?
| Module | What it covers |
|---|---|
| What is a neural network? | Layers, weights and activations, drawn out. |
| Gradient descent and backpropagation | How networks learn, step by step. |
| Transformers and attention | How modern language models work inside. |
What we liked, and what we didn't
What we liked
- Outstanding animations
- Builds real intuition
- Short episodes
What we didn't
- No exercises
- No certificate
What's the catch?
It's a video series, not a course. You'll understand a lot and build nothing unless you pair it with one.
What should you take before it?
Nothing. This is a starting course: you need no AI or coding background.
What should you take after it?
- Practical Deep Learning for Coders
Practical Deep Learning for Coders has 9 lessons of about 90 minutes, costs nothing and has no certificate. You deploy your own model by the end of lesson 2.
- Neural Networks: Zero to Hero
Neural Networks: Zero to Hero is 8 free YouTube videos, about 14.5 hours, where Andrej Karpathy builds a GPT from scratch in code. No certificate.
How we rated it: 9.1 out of 10
| Criterion | Score out of 10 |
|---|---|
| Clarity | 10 |
| Hands-on practice | 2 |
| Up to date | 8 |
| Depth | 8 |
| Truly free | 10 |
So should you take it?
Watch this whenever the maths behind neural networks feels like a black box. No code, but the best visual intuition you'll find anywhere, free or paid.
Where to go next
- AI learning path for non-coders
A learning path that includes Neural Networks (video series).
- Generative AI for Everyone
What large language models can actually do for you and your team, without writing a line of code. Andrew Ng teaches it in 6 hours on Coursera, certificate paid.
- Machine Learning Crash Course
Google's Machine Learning Crash Course has 12 modules and takes about 13.5 hours by Google's own timings. It is free, with quiz badges and no certificate.
- CS50's Introduction to AI with Python
CS50's Introduction to AI with Python runs 7 weeks with 12 projects, costs nothing and gives a free CS50 Certificate if you score 70% on every project.
Last checked .
Not sure this is the one?
Answer two questions and we'll point you to the course that fits where you are today.