The interactive parts don't work e.g. in http://neuralnetworksanddeeplearning.com/chap4.html

If you want to annotate the original, interactives and all, you can use something like https://hypothes.is/ (also open source)

I think Fermat's library seems great for annotating older static papers, but it the current version seems like the wrong format for this. Perhaps for interactives, just embed the original site with hypothes.is annotations?

You can see what that would like using their proxy: https://via.hypothes.is/http://neuralnetworksanddeeplearning...

Wow, I hadn't heard of hypothes.is before, that proxy implementation is awesome. I like the highlighting/commenting feature on Medium, for example, and this adds it to any document transparently, it looks like. Good stuff.

I think this is an absolutely fantastic idea. I think every field should do something like this for its "seminal" papers! I wanted to get something like this going for "A Mathematical Theory of Communication"[1] which was just posted [2] a week ago!

[1]: http://worrydream.com/refs/Shannon%20-%20A%20Mathematical%20... [2]: https://news.ycombinator.com/item?id=12079826

Hey HN, this is an experiment and we would like your help. We love Michael Nielsen's book and we think it's one of the best starting points to learn about Neural Networks and Deep Learning. Help us create the best place on the internet to learn about these topics by adding your annotations (comments, videos, lectures, blogposts...).

I love this idea. I'm kind of sad that there aren't more projects like this.

See also the description of the Memex in "As We May Think" by Dr Vannevar Bush: http://www.theatlantic.com/magazine/archive/1945/07/as-we-ma...