Hacker News Reader

I'd highly recommend course.fast.ai - it's focussed on deep learning, but is designed for beginners to get to a production stage.

View on HN

I'd second this, plus Jeremy and Rachael hang out on HN occasionally.

I've also worked my way through "Hands on machine learning with scikit learn and tensorflow" by Geron and have found it pretty approachable, up until tensorflow anyway.

But https://github.com/aymericdamien/TensorFlow-Examples helped with that.

Does deep learning encompass all ML though? While I agree it can be used for numerous tasks I don't think starting ML with deep learning is such a good idea.

Deep learning is easy and popular - it's just as good a starting point as anything else. No one would argue that linear regression isn't a good starting point, but only because it's not fashionable to dismiss linear regression.

Reply on news.ycombinator.com