One hypothesis is that there is a trend of non ML-familiar developers currently working on getting more grasp on ML. Such repositories provide something that e.g. web developers can take a look at, with reduced friction.

Disclaimer: I'm such a developer! (currently going through the last bits of https://www.coursera.org/learn/machine-learning) - but I've noticed other around me recently.

I up-voted this since I found it really helpful while working through Michael Nielsen's book on neural networks[1]. (I had chanced upon this repo a couple of months ago)

The code is actually based on the original code from the book (e.g.: can be seen from the variable names like 'nabla') , but written in a more succinct manner. Since I am relatively new to Python, I found it easier to follow this repo's code than the code in the book and used it as my reference implementation.

It's missing quite a few things like calculating accuracy, regularization, etc. but they are quite straightforward to implement.

[1] Neural Networks and Deep Learning by Michael Nielsen - http://neuralnetworksanddeeplearning.com

You said it yourself: when you want to learn something complex (like ML), it's usually easy to start with something with reduced complexity.

At least, that's why i clicked the link.

We aren't all working on machine learning. There will always be some people who are getting into it for the first time.

Hehe, you're probably of similar mind to PaulHoule who commented on my Ask HN thread - https://news.ycombinator.com/edit?id=12198327

Haha nice comic ! :-D