Lesson 1 - Deep Learning for Coders (2020)

In this first lesson, we learn about what deep learning is, and how it's connected to machine learning, and regular computer programming. We get our GPU-powered deep learning server set up, and use it to train models across vision, NLP, tabular data, and collaborative filtering. We do this all in Jupyter Notebooks, using transfer learning from pretrained models for the vision and NLP training.

We discuss the important topics of test and validation sets, and how to create and use them to avoid over-fitting. We learn about some key jargon used in deep learning.

We also discuss how AI projects can fail, and techniques for avoiding failure.

00:00 - Introduction
06:44 - What you don’t need to do deep learning
08:38 - What is the point of learning deep learning
09:52 - Neural Nets: a brief history
16:00 - Top to bottom learning approach
23:06 - The software stack
39:06 - Git Repositories
42:20 - First practical exercise in Jupyter Notebook
48:00 - Interpretation and explanation of the exercise
55:35 - Stochastic Gradient Descent (SGD)
1:01:30 - Consider how a model interacts with its environment
1:07:42 - "doc" function and fastai framework documentation
1:16:20 - Image Segmentation
1:17:34 - Classifying a review's sentiment based on IMDB text reviews
1:18:30 - Predicting salary based on tabular data from CSV
1:20:15 - Lesson Summary

[ricardocalleja]

I really admire you guys for such a terrific job. Thanks, many Thanks. God bless you!

[salivona]

"We are not going to teach 2 hours about sigmoid..." OMG Thank you for practical course! Got the book and recommend to all :)

[MuruganR-tgyt]

Thanks for added Tamil Subtitle. It is great way to learn concepts in native language. Thanks a lot 😊

[pythonbi]

I started my machine learning journey by building a classifier for my algo trades and now working on the hard part to improve the accuracy of it.... Thanks Jeremy and team for sharing the knowledge...admire the efforts

[JustinMitchel]

Yes the legend returns! Definitely bought your book a while ago. Thanks for the hard work!

[RSUtsha]

Thank you very very much for your hardwork and effort and for bringing us this amazing framework and course. I can't really say enough that how much I admire you all.

[aseedb]

I wanted to continue the course of last year after a long break. Nice surprise, there is a new one! I have ordered the book. Looking forward to receiving it!

[gopesh]

Only good thing about 2020
Thank you sooo much Jeremy ❤️

[morttalzera]

I have to say Jeremy, each video I watch about, the more I like you.

[kilebox]

Omg r u kidding i just watched whole series;)

[strangersinlondon_]

I cried hearing the top-down approach. I struggled horribly with my BS Physics course because all my professors with one exception taught everything from the bottom-up. I have strong academic inclination from when I remember learning anything, and I always NEED to know the big picture first before going through the details. Thank you for pointing this out now 4 decades after I told my mum at 7 years old that I wanted to be mind-minded instead of sports-minded. Ironically, it's the sport analogy that made everything clear to me now. Again, thank you for the learning method beyond this career-changing content.

[maxkasper]

I am so so excited for the new course, thank you so much for providing these great lectures🙏

[arnolddalby]

Brilliant, I will put your book on my buy list for September. Bless you all for your good work.

[The]

Thanks for Tamil subtitles...all my friends loved it

[toequantumspace]

Hi Jeremy thanks for posting a new course!

[gusbakker]

That's some really nice start of the video.. by assuming that even if we cannot build AGI systems at least we can do amazing things with deep learning!
I'm very curious about the new Book!

[harshil_]

The YouTube Algorithm outdid itself this time.

[olee_]

This guy is a saint, believe it or not 2 people tried to cancel him after one of his talk for saying someone else was wrong... SMH. Sometimes I feel like we dont deserve people like Mr Howard.

[arvinflores]

as a person who only use python for sympy and sometimes matplotlib. Holy I'm confused as hell lol but I uploaded my own cat's picture, and it was identified as a cat, that's a win for me I guess. Hopefully I can adapt to this top-down approach in the later videos. Cheers

[mostafakira]

Finally a course dig deep in transfer learning, Thank you so much guys