Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Practical Deep Learning for Coders 2022

fast.ai

Post reply on HN
Print view View original

81–86 of 86 posts

Re: Practical Deep Learning for Coders 2022

#81

Post by perfopt »

nmfisher wrote: post #31
perfopt wrote: post #10

This is awesome. One question I have always had - is the research on applying DL for images the most developed compared to other things? Even DL used for audio processing (classification, separation etc) seems to convert audio to spectral graphs and apply DL to that. Changing a problem to be expressed as image inputs will be an advantage when using DL as a solution. Would you agree ?

Working with a spectrogram is definitely similar to working with an image, and it's interesting to think why that's the case. Take convolutional models, for example. Very effective for working with images because they're (a) parameter efficient, (b) learn local/spatial correlations in input features, and (c) exploit translational invariance. As an oversimplification, we can train models to visually identify "things"…

Thanks for that note. I have an audio classification hobby project (for now). Could you point me to things I should learn to get better at audio classification and generation?

Your comment about time domain making audio difficult - before doing some research I thought it would make it impossible. But looks like people have had some success with using spectrograms of short audio samples. What techniques should I try to learn to deal with the time component of audio?

One idea is to chop up the audio into short samples and treat the resulting images as a video. Then look at DL algorithms that deal with video. Am I on the right track?

Re: Practical Deep Learning for Coders 2022

#82

Post by cinntaile »

gandalfgreybeer wrote: post #73
qwrshr wrote: post #51

Earlier quoted context omitted.

out of curiosity, how much applied math should one bone up on? (Obviously the more the better, but diminishing marginal returns and all that.)

Bare minimum is basic calculus, basic linear algebra and basic statistics. By basic, I probably mean first courses for those in most undergraduate programs. I disagree with needing none and just going along as needed. That’s how you have machine learning models that look like they work but you don’t understand why they work so there might actually be problems.

That's not quite what I said. I said to look things up if you don't understand, I made the assumption that the one asking has taken maths courses before. I interpreted bone up on as refreshing old knowledge but I could be wrong.

Re: Practical Deep Learning for Coders 2022

#86

Post by uwuemu »

jph00 wrote: post #28
nindalf wrote: post #26

Earlier quoted context omitted.

I tried the 2021 course but I didn't finish. I think the biggest friction for me was using the remote machine. I wasn't able to make steady progress like I do with my offline learning projects. How far away is the fast.ai from working on a Mac? PyTorch recently gained support ( https://pytorch.org/blog/introducing-accelerated-pytorch-tra... ) but that's only the start. Is this something that is being worked on?

The good news is that every lesson in this course is actually run on Kaggle Notebooks, which is a free cloud environments including GPUs. So you don't need to set up anything and it runs on any computer with a modern web browser! Mac support for all the libs used in the course will probably continue to improve in the coming months and there should be no reason you won't be able to run the stuff for the course locally…

I think last time I tried this, I kinda gave up as soon as it got to the point of hand-waving hardware and telling you to run notebooks on a third party's web service. How is that democratizing AI? It's the very opposite! Not good. What is the intended audience here? Uni-level students will learn most of these within their programs if they're interested in AI. So they're not really it. Is the intended audience "coders"? If so, most of these "coders" will have to somehow get their employer on board (typically a corporate entity very much NOT interested in "coding" something in a 3rd party ecosystem) or do it themeselves. Hence, I want to take an RTX 3080+, 64+ gb of ram, big ass SSD and I want to get through the training. Not learn some basics on somebody else's platform (come on, even from the pov of OS, running both training AND notebooks on some 3rd party's private platform is so against the idea of open source...) and call it a day. What use is that? That may be enough if you want to be a cog in somebody else's machine, but not if you want to do something useful by yourself (I say "may" because big tech generally isn't interested in your "mad AI skillz" unless you also have a student loan backed piece of paper proving you successfully learned that for the last couple of years).

There will always be smart individuals and talented small teams that can successfully integrate AI into their products, but it's not thanks to the courses like this.

If you're going to aim at coders, there has to be clear path demostrated from the beginning to the end. From starting up your first notebook on your local dev machine and running training on your local training machine to setting up inference in the final app (.net app or whatever)

Post reply on HN