You are right, the write-up isn't meant for newbies to the topic. I'll definitely think about updating the intro to reflect that.
Regarding the ML series: aren't there already quite a few introductory series into the topic, which can be referred to? Because the text I wrote on the project page wasn't intended to be a guide of how to build a project like this, but rather to give a glimpse of how such an algorithm might work. But anyway I must say that I really like your concept of an interactive tutorial series. Maybe I'll write a guide to a project like this in the future; would also contribute if someone else does (to anyone out there).
I definitely hope you stick around and keep posting interesting stuff you're working on. It's one of the main reasons I'm a regular visitor, and it inspires me to keep tinkering with my own projects!
> Regarding the ML series: aren't there already quite a few introductory series into the topic, which can be referred to?
I agree with the earlier poster that upon seeing what you did I kind of expected a tutorial explaining how to get there. I don't think you'd have to provide such a tutorial, of course, but I think setting expectations and ideally even linking to good 'introductory series into the topic' would be very much appreciated.
Personally I like to be presented with some end result that might take quite a bit of work to recreate. Being frustrated upon realizing that there's quite a bit of work ahead works well for me. But I especially love it when I'm given some gentle pointers towards next steps, so for me at least adding such pointers would make your article/demo even better.
For example: I had been interested in this 'lisp' thing for a while. I'd read a few short articles explaining the basics and why lisp is cool and so on, but I never dove in.
Then, one day, I read an article that presented some (relatively) idiomatic code in js/python/ruby/I don't remember, and a much shorter equivalent in, iirc, Clojure. The latter made no sense to me, but I was so curious about what was going on, that I continued reading the rather long article.
After finally vaguely understanding what the Clojure code was doing, I was so excited that I immediately went on and spent a few weeks tinkering with Clojure. Somehow, for me, it took a `look at what you'll eventually be able to do` type article to tickle me in the right way to actually sit down and bother learning clojure.
About the series: there are quite a few of those around, but most of them are difficult to follow for the mathematically challenged. So, can you explain it without needing to include mathjax.js? If so, you would definitely stand out. :)
There is [0] that looks promising though.
[0] https://medium.com/@dhruvp/how-to-write-a-neural-network-to-...
I only say this because as I was reading it, I was looking at it from that standpoint, because on initial review, with the 2D nature and the "cartoonish" graphics (nothing wrong with that - in fact, it makes it very approachable), there is a subtle expectation that this demo might be for beginners in the field.
I continued reading, and as I read the technical background, it became quickly apparent that this was not using a simple multi-layer backprop ANN, but something seemingly more advanced, with little to go on to understand how it worked. There is enough there that an interested learner could research the topic, but I think a beginner to the topic would quickly become overwhelmed, because none of the various jargon and other terms ("hyper-parameters? what the hell are those?", I can hear such a newbie exclaiming) have been defined.
I don't believe you ever intended this to be understood or used as an introduction or a beginner's tutorial to machine learning, but because it appears like it could be, mentioning that it isn't at the beginning might be appropriate.
Furthermore, this could be an opportunity for you or someone else to create an approachable series of interactive "run-in-the-browser" javascript machine learning tutorials, starting with the basics, and culminating in something like this. Such a series would need to be planned well, and first defined what should be shown and in what order (ie - Do you discuss basics of linear algebra or probability? Do you incorporate classic ML techniques in the series along with neural networks?). Hmm - now that I think about it, I can actually envision a whole sequence of series of lessons, building from the bottom ("What is a vector?") on up...
Ultimately - I found this demo fascinating and interesting. Thank you for sharing it!