Andrew Ng's machine learning course on Coursera is a good introduction to the theory. https://www.coursera.org/learn/machine-learning
Ask HN: In 2022, what is the proper way to get into machine/deep learning?
11–20 of 211 posts
Re: Ask HN: In 2022, what is the proper way to get into machine/deep learning?
#12Follow the HuggingFace Colab notebooks. They are well-written and language-related AIs are a great way to get started because you'll naturally have a feeling for what it should produce. Afterwards, do a statistics class. Most algorithms these days are based on softmax, meaning the cross-entropy between two discrete/continuous probability distributions. There's a lot of choice in which distribution to use to model wha…
Great suggestions and perspective! Thanks!
Re: Ask HN: In 2022, what is the proper way to get into machine/deep learning?
#13Andrew Ng's machine learning course on Coursera is a good introduction to the theory. https://www.coursera.org/learn/machine-learning
I was about to share the same link, really good solid foundation and understanding of what is behind ML
Re: Ask HN: In 2022, what is the proper way to get into machine/deep learning?
#14FastAI. Specifically "Deep Learning for Coders" which was recently updated.
https://course.fast.ai/
Do what the instructor recommends: watch each lesson once in its entirety and then re-watch it while playing along. But don't just type their commands verbatim. Try and do something slightly different.
Re: Ask HN: In 2022, what is the proper way to get into machine/deep learning?
#15Fast.ai
Re: Ask HN: In 2022, what is the proper way to get into machine/deep learning?
#16You could do worse than go back and make sure your foundation maths is
solid. Revise some Discrete Maths books and understand identification,
classification, sets, equivalence... Make sure you've a solid ground
on concepts like dimensions, functions, differentiation, integration,
extrapolation, interpolation, then toughen up your Linear Algebra,
optimisation, solving, regression, before getting into approximation
and gradient descent.
Sure, most of this sounds as dull as a broken clock, but in my observation it makes the difference between students who can just use machine learning tools by copying textbook cases and adopting a lot of fancy new terminology, and those that understand what they're doing.
That difference really kicks in once you get off the beaten track of popular use-cases, into applying ML to new, unproven applications. Then you need a deeper understanding of why some algorithms may be useful and others are inappropriate.
Re: Ask HN: In 2022, what is the proper way to get into machine/deep learning?
#17Have you taken undergraduate-level linear algebra, multivariable calculus and probability? Those are the prerequisites if you want to approach things a bit more rigorously. If you've covered them, get something specific to ML.
I like Hands-On ML... by Geron as a decent intro to ML book. FastAI seems a bit overrated to me - I didn't like that it uses its own helper library or the teaching style but it obviously works for other people.
Then there's more exhaustive books on theory - Elements of Statistical Learning, Pattern Recognition and Machine Learning, Bayesian Reasoning and Machine Learning, Murphy's books on probabilistic ML etc. But obviously the theory books have a lot of overlap with each other so there will be lots of material to skip after you've read one or two of them.
Re: Ask HN: In 2022, what is the proper way to get into machine/deep learning?
#18There are already good recommendations here for getting into the "standard practice" of ML.
To really understand what is going on though, the path I am having some early success with (as a long time developer / data pipeline guy, but newly into the standard python / ML practice) is to run through Kochenderfer's "Algorithms for optimization" from 2019 (MIT press), including implementing the exercises, as optimization is the cornerstone of the majority of ML methods. Some of the most fun I've had in a long time.
Freely available here:
https://algorithmsbook.com/optimization/
From there on, I'm less sure, but expect I might experiment with implementing my own deep learning methods just for fun, or similar.
Re: Ask HN: In 2022, what is the proper way to get into machine/deep learning?
#19There is the "high bias low-variance introduction to Machine Learning [for physicists]" -> https://news.ycombinator.com/item?id=17772211
Quotes from the comments:
> For all my hacker news peeps that wants to learn ML and/or DL, you need to drop everything right now, go print this on the office printer, and sit outside with coffee for the next two weeks and read through this entire thing. Turn off the computer and phone. Stop checking HN for two weeks. Trust me, nothing better than this will come around on HN anytime soon.
> The authors are wrong to label this book as useful only to people with a physics background, and in fact it will be useful for everyone who wants to learn modern ML.
Re: Ask HN: In 2022, what is the proper way to get into machine/deep learning?
#20It might not be exactly what you're looking for but I stumbled upon this video by Sebastian Lague the other day: https://youtu.be/hfMk-kjRv4c
As someone who's only ever dabbled into minimaxir's GPT-2 packages this was an extremely approachable exploration (and explanation) of how a neural network works. I can't recommend it enough.