Practical Deep Learning for Coders: Lesson 1
Jeremy Howard2 HN recommenders · 2022–2023
610K views · course · dated · Uploaded 2022-07-21
Lesson 1 of fast.ai's Practical Deep Learning for Coders, taught by Jeremy Howard. It takes coders from running code in a Jupyter notebook straight into training a real image model.
HN considers the course one of the best hands-on ways into deep learning, praising the code-first teaching style.
1:03:43How to Speak
MIT OpenCourseWare
2:25:52The spelled-out intro to neural networks and backpropagation: building micrograd
Andrej Karpathy
57:151. Introduction to Human Behavioral Biology
Stanford
1:21:52LEADERSHIP LAB: The Craft of Writing Effectively
UChicago Social Sciences
18:40But what is a neural network? | Deep learning chapter 1
3Blue1Brown
1:11:40MIT's Pathway to Fusion Energy (IAP 2017) - Zach Hartwig
MIT Plasma Science and Fusion Center
52:29Stanford's Sapolsky On Depression in U.S. (Full Lecture)
Stanford
54:56Justice: What's The Right Thing To Do? Episode 01 "THE MORAL SIDE OF MURDER"
Harvard University
3 comments from Hacker News
I'm super excited about the Audio AI space, as it seems permanently a few years behind image stuff - so I think we're going to see a lot more of this. If you're interested, the idea of applying Image processing techniques to Spectrograms of audio is explored in brief in the first lesson of one of the most recommended AI courses on HN: Practical Deep Learning for Coders [VIDEO]
Practical deep learning for coders (2022 edition) By Jeremy, who is the founding researcher at fast.ai. Three things I love about this series 1. Jeremy seems like a power user of Jupyter notebook and uses them beautifully to run the lectures. The book on fastai is also written in Jupyter notebooks. 2. The lectures are super hands on - Jeremy actually fires up a jupyter notebook and runs code which often surprises him 3. I love how he describes he deep dives into a specific Kaggle competition. Describes in great detail his own attempts at getting up the leaderboard. It's almost like watching a poker player reveal her decision process before they make a move. [VIDEO]
> weights of a model, that a domain expert can tweak by hand This sounds similar to how image recognition was done before deep learning [1] [1] [VIDEO]