I really want to learn about Machine/Deep Learning. I tried to start with some ML courses and online resources but I got intimidated when I saw that it required really good background in Maths. I do have basic intro to Calculus, but I don't know much. It seems to get really good at ML, you need to know a lot about Maths. I'm sure some of you have already crossed this hurdle, so I'm really interested to learn about your experience. I did google search and encountered this link[1] but by looking at the resources, it seems that it's a lot of ground to cover. I feel overwhelmed, so I'm just looking to cover the minimal ground.<p>[1] https://www.quora.com/How-do-I-learn-mathematics-for-machine-learning
I wrote this comment a while ago but I think its still very relevant...<p>I wrote about this here: <a href="https://news.ycombinator.com/item?id=8767092" rel="nofollow">https://news.ycombinator.com/item?id=8767092</a> and here: <a href="https://news.ycombinator.com/item?id=9433316" rel="nofollow">https://news.ycombinator.com/item?id=9433316</a><p>Long story short, the biggest mistake I see people making is not actually rolling up their sleeves and learning the math.<p>People are often content to watch hour after hour of Udacity, Khan academy and Coursera videos but the applied follow up is where most people drop off. At the very least any course work should be followed up by something practical like a kaggle exercise to prove that you can apply the technique you just learned. Consider the benefit of just watching videos vs doing actual applied work.<p>On one hand if you just watch videos you might learn alot but how do you prove that to someone hiring you? On the other hand if you sit down and spend a week attaching a Kaggle excise then at the very least you have something to point people to, to show that you can apply machine learning techniques.<p>My recommendation has always been to read the first 5 chapters of Introduction to statistical learning: <a href="http://www-bcf.usc.edu/~gareth/ISL/" rel="nofollow">http://www-bcf.usc.edu/~gareth/ISL/</a><p>and if you fly through it then sample Elements of statistical learning <a href="http://statweb.stanford.edu/~tibs/ElemStatLearn/" rel="nofollow">http://statweb.stanford.edu/~tibs/ElemStatLearn/</a> for the topics that you want to learn.<p>If intro to statistical learning is too advanced, then go to Khan academy and work your way through their statistics videos.
From my experience you can bucket people into skill level by looking at how they attack a new problem.<p>Beginners tend to start by saying they'll need a hadoop cluster and spend the next week setting up a pipeline.<p>Intermediate people tend to jump into R or scikit and try to model the problem with a small subset of data and the library and technique they know best.
The advanced people tend to flesh out their hypothesis first and then work out the math and then jump to modelling with a small set of data and finally move to a cluster.
To quote a mathematician you might have heard of, "μή εἶναι βασιλικήν ἀτραπόν ἐπί γεωμετρίαν", that is, "there is no royal road to geometry", that is, there's no easy way to get there without doing it.
This may not be the answer you were hoping for, but if you do not have the background already to do this sort of thing and if you are not already stubborn enough to start learning mathematics on your own, school may be for you. I assume you are not stubborn enough to start doing so because you have not done so already.<p>A short master's (3-4 semesters) is about enough to have all the math background + some application classes.
Yes, it's a lot of turf to cover. Until very recently, most of it was at best, barely touched on in a typical undergraduate curriculum. But here's one source you'll see cited a lot:<p>An Introduction to Statistical Learning<p><a href="http://www-bcf.usc.edu/~gareth/ISL/" rel="nofollow">http://www-bcf.usc.edu/~gareth/ISL/</a>
To understand ML you'll at least need a good understanding of vector differential calculus and linear algebra. There are many free ressources available for learning math today, MOOC's, free textbooks, etc. but if you were studying this in college it would amount to at least 2 semesters of courses that many people find quite challenging. So while you can probably learn this on your own it will likely require quite a significant time commitment as well as strong self-discipline.<p>You may be able to make some use of existing ML models and libraries without a deep understanding of the methods however.