Hi folks. Nice to see our new free (and ad-free) course here on HN! This course is for folks that are already comfortable training neural nets and understand the basic ideas of SGD, cross-entropy, embeddings, etc. It will help you both understand these foundations more deeply, since you'll be creating everything from scratch (i.e. from only Python and its standard library), and to understand modern generative modeling approaches.<p>We study and implement a lot of papers, including many that came out during the course, which is a great way to get practice and get comfortable with reading deep learning literature.<p>If you need to get up to speed on the foundations first, you should start with part 1 of the course, which is here: <a href="https://course.fast.ai" rel="nofollow">https://course.fast.ai</a><p>If you've got any questions about the course, generative modeling, or deep learning in general, feel free to ask!
I just finished this! My thoughts:<p>I recommend it. I feel I can now read an arbitrary paper, frown a lot, and eventually understand what it's talking about - to the point where I can implement my own buggy version. And hey, I built my own stable diffusion!!<p>I found the previous version of this course[1] to be a good complement: it's older (predates SD) but I feel it explains core concepts slightly better. Very understandable given how the close to the bleeding edge this new version is...<p>Perhaps an even better complement was Karpathy's famous course[2] - similar material but builds towards GPT instead of SD. The fastai coding style is somewhat esoteric (to me) so it was helpful to contrast with Karpathy's more familiar style. I recommend doing both courses. Also I believe the fastai folks are planning a part 3 which covers LLMs; looking forward to that.<p>Concepts from part 2 helped my hobby project, a 7-day forecast of renewable electricity and power price[3].<p>Feels pretty great to have built my own Stable Diffusion and GPT! I am grateful to Jeremy and Andrej.<p>[1] <a href="https://course19.fast.ai/part2" rel="nofollow">https://course19.fast.ai/part2</a><p>[2] <a href="https://karpathy.ai/zero-to-hero.html" rel="nofollow">https://karpathy.ai/zero-to-hero.html</a><p>[3] <a href="https://greenforecast.au/" rel="nofollow">https://greenforecast.au/</a>
I audited this course - I say “audited” because I didn’t have time to do the homework; I just watched the lectures and spent what time I could playing around in Colab building some toy models. This is very much a full time university level course and you should treat it that way if you intend to complete it properly. You will need to reserve 10 hours per week for the homework - at least.<p>I enjoyed how Jeremy and his teaching assistants step through every detail so that you can understand how these fantastically complex systems actually work, from the ground up. Nothing is glossed over or taken for granted.<p>Much of the course material is building an AI programming framework from scratch. It’s well worth the hassle; I now at least have an intuition about how these systems work, rather than a glossed over impression with many holes. The other thing I greatly appreciated were the insights from other classmates in the forums. Some people way smarter than me took this course and Jeremy would incorporate their flashes of insight into the lectures.<p>I give this course a 10/10 and I hope my life gets a little easier so that I can get back to the lessons and finish the homework one day.
I have worked on the course with @jph00 and it's been an incredible experience! This is one of the most cutting edge courses about deep learning and diffusion models. Highly recommend folks check it out!<p>Link for more info: <a href="https://www.fast.ai/posts/part2-2023.html" rel="nofollow">https://www.fast.ai/posts/part2-2023.html</a>
I just used fastai last week for an experiment at work. I have no to little DS experience, but quickly skimmed through part1.<p>Quite easily I managed to use a pretrained resnet to do some quite astonishing things on completely unrelated pictures we have. And it only took like 10 epochs at ~4 seconds each, so less than a minute of training and it was already quite good.<p>What I did was that we have taken pictures of things during a process. At that point, I know what the volume should be. So used ~thousand of those images to train a regression model to estimate volume of the thing in the image.<p>Then I run the model on other images and compare what the model thinks is the volume compared to what it should be. When it's off, the algorithm is mostly correct and we have an error on our side.<p>Quite astonished about how quick and easy this was to do with the high level api of fastai. Took me 2-3 days.
This is cool, but I have a fundamental question.
Why learn machine learning when all the machines will learn how to create and control themselves and powerful elites will offload the burden of governments to control us?<p>Or we race ourselves to fulfill the last jobs on earth? Is this progress for humanity or enslavement and the end of our species? I am serious. This question is honest. Maybe my IQ is too low to understand the logic of this innovation.<p>Maybe I have seen too much tech implementation doing bad stuff to humans, who knows? Please, enlighten me.
Part #1: <a href="https://course.fast.ai/Lessons/lesson1.html" rel="nofollow">https://course.fast.ai/Lessons/lesson1.html</a>
Would it be possible to have a transcription of the videos? I have never been able to follow a video for learning, for me the video format if like someone else controlling the way I learn.I much prefer to be able to design my own schedule in text. By using text I am able to skim quickly and select only those parts I consider important. Maybe other people are able to do that with video but I am not in that group.
I've watched all of the fastai tutorials. I've screwed up by not going through and actually writing the code, but I hope to do it again and do it right this time. My biggest question is if this the whole part 2 course or still the 2-3 preview courses released around last November?
The fast.ai courses are exceptionally good for getting started and learning the concepts, but, once you've mastered an intuitive understanding of the techniques, I highly encourage people to dig deeper into the concepts - specifically, reverse SDEs, stochastic calculus, optimization, score matching.<p>Jeremy does an excellent job making the content approachable, but, if you want to go beyond being an excellent practicioner, you cannot skip the theory bits.
my nephew who is going to college this fall at east coast said, "what's the point of CS major anymore" and i asked "what do you mean" and he goes " ChatGPT".
This is very cynical coming from 16 year old; however, got me thinking about impact of Chatgpt on peoples' mind about learning ML/AI if chatgpt can do it all!
This looks awesome, however I probably need to do a bootcamp with real people to compete and have comradery with to actually retrain on the basics in this.<p>It doesn't matter where in the world this is (I like to travel), but does anyone have a recommendation for in person bootcamps on AI?
Why would I want to learn fast.ai...<p>I feel that while this course is surely superb, I don't want to invest time in a new framwework. What's your opinion?<p>We've got lightning, fast.ai, and another one that I forgot about... why?
This is awesome!<p>I loved the previous FastAI courses, and the top-down approach taken in them is really fun to go along with.<p>I guess now it's time for an LLM-themed course?