Hacker News Reader

If you've got a lock on calculus, programming, and linear algebra, then you've got the skills to understand deep learning. Most time spent working on DL is not in the megamath part, it is in finding good network structures to optimize results.

View on HN

I think a lot of resources out there at the moment are full of ML jargon and math. And a lot of new stuff that is coming out attacks the absolute beginner. This kind of sucks .. I started using torch, familiar with old fashioned NN and just wanted to quickly get up to speed on convolutional networks. It has been a PAIN (resources I find are either too deep or not deep enough). In any cases .. thanks for putting your links .. they were most helpful.

You are right that most resources aren't that great at showing you the way. There is a lot of grinding to get past obstacles.

We are trying to address this soon!

Reply on news.ycombinator.com