We are big fans of posts and videos that try to give you a gut-level intuition on technical topics. While [vas3k’s] post “Machine Learning for Everyone” fits the bill, we knew we’d like it from the opening sentences:
Machine Learning is like sex in high school. Everyone is talking about it, a few know what to do, and only your teacher is doing it.”
That sets the tone. What follows is a very comprehensive exposition of machine learning fundamentals. There is no focus on a particular tool, instead this is all the underpinnings. The original post was in Russian, but the English version is easy to read and doesn’t come off as a poor machine translation.
The article starts off with some pretty basic ideas but goes into quite a bit of detail about different machine learning strategies before talking about real-world applications such as spam filtering and credit scoring. If you know what bagging vs boosting means and can explain the difference between a convolutional network and a recurrent network, this post might not be for you. But for everyone else, it is a great common-sense exposition of a lot of fundamental topics.
There are not custom videos as far as we could see, but the text does link to some excellent ones from [3Blue1Brown] and others that go into more details, like the one below.
If you want an introduction to the technology side of things, you can play around in your browser. Or start with our TensorFlow introduction.
Been looking for a primer on this forever. Thanks for posting. Very helpful. hackaday rules.
“If you want an introduction to the technology side of things, you can play around in your browser. Or start with our TensorFlow introduction.”
Or play a game.
https://store.steampowered.com/app/619150/
The examples also give a good insight into Russian daytime drinking culture.
Judging by the number of comments here, it seems that this subject is much less popular than a flying toilet. I found the article fantastically useful; a high-level intro to machine learning with wonderful illustrations. Better than the last book I bought on the subject. Will keep this one bookmarked.
Yes, it’s pretty weird this lack of interest. Certainly the best thing I’ve read on Hackaday for a while, not to say the other stuff was bad, but this was particularly inspiring. The videos are also very well done and fooled me into believing I understood it all, even if I could not explain it to someone else!