What maths must be understood to enable pursuit of either of the above fields? are there any seminal texts/courses/content which should be consumed before starting?
Ask HN: What maths are critical to pursuing ML/AI?
1–10 of 139 posts
Re: Ask HN: What maths are critical to pursuing ML/AI?
#2You absolutely need a solid grounding in multi-variable calculus, linear algebra, probability theory and information theory. It will also be helpful to be well versed in graph theory.
In my opinion one of the best starting points is "Information Theory, Inference and Learning Algorithms" by David MacKaye. It's a bit long in the tooth now, but it is still one of the most approachable and well written books in the field.
Another old book that stands up very well is "Probability Theory: the Logic of Science" by E. T. Jaynes.
"Elements of Statistical Learning" by Tibshirani is also good.
"Bayesian Data Analysis" by Andrew Gelman is another great read.
"Deep Learning" by Ian Goodfellow and Yoshua Bengio is useful for getting caught up with recent advances in that field.
Re: Ask HN: What maths are critical to pursuing ML/AI?
#3You absolutely need a solid grounding in multi-variable calculus, linear algebra, probability theory and information theory. It will also be helpful to be well versed in graph theory. In my opinion one of the best starting points is "Information Theory, Inference and Learning Algorithms" by David MacKaye. It's a bit long in the tooth now, but it is still one of the most approachable and well written books in the fiel…
you mean i cant just bang out some ipythons and the matrix forms around me?
thanks for the list! the only roadblock i've ran into getting into many of these topics are book prices :O usually they are pretty steep
Re: Ask HN: What maths are critical to pursuing ML/AI?
#4You absolutely need a solid grounding in multi-variable calculus, linear algebra, probability theory and information theory. It will also be helpful to be well versed in graph theory. In my opinion one of the best starting points is "Information Theory, Inference and Learning Algorithms" by David MacKaye. It's a bit long in the tooth now, but it is still one of the most approachable and well written books in the fiel…
you mean i cant just bang out some ipythons and the matrix forms around me? thanks for the list! the only roadblock i've ran into getting into many of these topics are book prices :O usually they are pretty steep
Actually, the MacKaye, Jaynes and Goodfellow books are available for free online. Enjoy!
Re: Ask HN: What maths are critical to pursuing ML/AI?
#5Stanford EE263 is very spicy http://ee263.stanford.edu
Re: Ask HN: What maths are critical to pursuing ML/AI?
#6You can learn the required maths along the way through Andrew Ng's deep learning course at coursera.
Re: Ask HN: What maths are critical to pursuing ML/AI?
#7You absolutely need a solid grounding in multi-variable calculus, linear algebra, probability theory and information theory. It will also be helpful to be well versed in graph theory. In my opinion one of the best starting points is "Information Theory, Inference and Learning Algorithms" by David MacKaye. It's a bit long in the tooth now, but it is still one of the most approachable and well written books in the fiel…
I disagree that you need a solid founding in information theory. Almost all that I've seen about IT in ML is minimizing the KL divergence, which can be learned by browsing the wiki page.
Re: Ask HN: What maths are critical to pursuing ML/AI?
#8You absolutely need a solid grounding in multi-variable calculus, linear algebra, probability theory and information theory. It will also be helpful to be well versed in graph theory. In my opinion one of the best starting points is "Information Theory, Inference and Learning Algorithms" by David MacKaye. It's a bit long in the tooth now, but it is still one of the most approachable and well written books in the fiel…
You can actually get the latest edition of Elements of Stastical Learning for free as a (legal) pdf from the author!
Re: Ask HN: What maths are critical to pursuing ML/AI?
#9It depends on how deep you want to go and what your goals are, but I'd say that CuriouslyC pretty much nailed it. Multi-variable calculus, linear algebra, and probability / stats are definitely the core.
If you're interested in finding more "freely available online" maths references, check out:
http://people.math.gatech.edu/~cain/textbooks/onlinebooks.ht...
http://www.openculture.com/free-math-textbooks
https://open.umn.edu/opentextbooks/SearchResults.aspx?subjec...
https://ocw.mit.edu/courses/online-textbooks/#mathematics
https://aimath.org/textbooks/approved-textbooks/
There's also a TON of high-quality maths instructional content on Youtube, Videolectures.net, etc. For example, there's some really good stuff by David McKay (also mentioned in CuriouslyC's post) here:
http://videolectures.net/david_mackay/
Be sure to check out Professor Leonard:
https://www.youtube.com/user/professorleonard57
Gilbert Strang:
https://www.youtube.com/results?search_query=gilbert+strang
and 3blue1brown:
https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw
as well.
Re: Ask HN: What maths are critical to pursuing ML/AI?
#10Statistics and Probability - For non-math background, Openintro.org with R and Sas lab is a good one. Khan academy videos on the same again makes a lot of concepts easier.
http://www.r-bloggers.com/in-depth-introduction-to-machine-l... Introduction to Statistical Learning http://www-bcf.usc.edu/~gareth/ISL/ (Rob S and by Trevor H, Free I guess) for more in depth, Elements of Statistical Learning by the same.
Linear Algebra (Andrew Ng's this part in Introduction to Machine Learning is a short and crisp one)
If you're not scared by Derivatives, you can check them. But you can easily survive and even excel as a data scientist or ML practitioner with these.