Hacker News Reader

Comment by thenomad | Hacker News Reader

There seem to be a few of these "learn deep learning without heavy math" courses popping up, for which I'm profoundly grateful.

Have people found any of them to be particularly outstanding? I'd be interested - and I suspect many HN readers would be - to hear recommendations.

View on HN

I've been really enjoying http://course.fast.ai/

Within a few hours of starting the course you'll have submitted an entry into the Kaggle Dogs vs Cats competition that scores in the top 50% of entries and achieves 97% accuracy. It's designed for coders who don't have a PHD in math. It's a very top-down approach, where you only get into mathematical details once you understand the high level models being used.

I find the lectures from Jeremy Howard [1] very helpful. He points out what seems to work and what doesn't and explains things very well. I'm up to lecture 4 and enjoyed them all.

I also like Andrej Karpathy's thorough explanation for backprop in his Lecture 4 cs231n video. The links to the videos are removed from the course page [2] for some reason, just google "cs231n video" and you will find the youtube links. The page on CNN is pretty good.

[1] http://course.fast.ai/

[2] http://cs231n.github.io/

Andrew Ng's Machine Learning on Coursera is a good for building some solid foundations in ML in general. Keep in mind it's not limited to Neural Networks. The math is kinda light, you either seek to understand it or trust that it works and focus on the ML principles.

> The math is kinda light, you either seek to understand it or trust that it works and focus on the ML principles.

This is accurate and also why I dropped out pretty quickly.

Reply on news.ycombinator.com