Neural networks for hackers
A short, practical, step-by-step guide to programming neural networks
This is course on deep learning for people who want to dive straight in! Without dwelling too much on theory, this course provides everything you need to start building stuff using neural nets.
The entire course can be completed in less than 5 hours. Opportunity cost is the most expensive part of education, so this class distills everything you need to know - otherwise scattered in papers, books, classes and videos - all into one place. By the end of the class, you will know how to write an AI agent to play the Atarti video game Ms. Pacman.
No prerequisites other than knowing how to code, preferably some Python, and a decent grasp of calculus-level math!
Covers:
- a broad overview of algorithms used in neural networks - in plain English
- what software packages and frameworks to use
- training models using GPUs, setting up a cluster in the cloud
- understanding the vocabulary used in deep learning academic papers
- how to keep up with the deep learning literature
- interesting project ideas so you can start building right away
Educational discounts: If you are a student, or want to buy this course in bulk for a class of students, please email me, I am happy to offer discounts.
What the course contains:
- A series of short, clear blog posts explaining important concepts in neural networks
- Audio recordings of each blog post, so you can learn passively
- 10 screencasts going from theory (papers) to practice (code)
- Reading lists and reading roadmaps for getting started with reading the deep learning literature
You can check out a sample post here or here.
Check out a sample screencast below:
Your Instructor
Computer graphics and vision programmer, formerly at Oculus and a16z. Cambridge Maths & CS grad.