Hacker Read

edwardio · 2014-04-20 19:16:37+00:00

You reminded me of something that does exactly this for machine learning. I posted it on the front page of HN (Metacademy).

nafizh | karma 4395 | avg karma 6.24 · | 2017-02-11 08:41:47+00:00

Wow, thank you so much for posting this link. I was looking for something like this before jumping into theoretical machine learning.

sgu999 | karma 1053 | avg karma 2.54 · | 2022-12-03 18:45:31

Very cool idea. That'd be a good way to see how it can generalize, actually. I suspect you'd quickly find its limits with something that isn't a toy example of an intro to machine learning.

jamestimmins | karma 4071 | avg karma 4.82 · | 2019-09-16 10:45:43

This is an awesome idea and a great learning project! It could be a cool tool for illustrating how different pieces of machine learning work together.

rhymer | karma 36 | avg karma 2.25 · | 2023-09-15 11:23:35

Agree, this is great! I wonder if there're some ML equivalent sites that present topics in a modular way?

falcolas | karma 33589 | avg karma 3.15 · | 2016-11-08 08:39:31

Something like the Ruby Koans for machine learning? I like that idea.

otoburb | karma 4390 | avg karma 2.85 · | 2014-04-21 16:14:28+00:00

Perhaps integration between this site and Metacademy would fit your needs. Metacademy was discussed in a different HN thread[1] recently, and is especially relevant to your query because it seems that the seed topics are machine learning and probabilistic AI.

[1] https://news.ycombinator.com/item?id=7617683

reply

dannyking | karma 235 | avg karma 2.76 · | 2014-04-21 16:18:00+00:00

We'd be totally up for that, Metacademy is fantastic - saw them yesterday too and had fun looking around. They seem to be very focused on Machine Learning at the moment, but could certainly make a great synergy once they've expanded their focus a little.

StavrosK | karma 1 | avg karma 0.0 · | 2010-10-27 11:56:06

Oh, I see. That's potentially very interesting (and I have a masters in machine learning, so it shouldn't be too hard to pull off). Send me an email and let's see if we can whip something up quickly?

amalag | karma 2058 | avg karma 2.03 · | 2013-04-10 14:27:58+00:00

Very nice idea. Can you give more detail about what kind of machine learning you employed?

vinceguidry | karma 12286 | avg karma 2.49 · | 2019-07-19 15:34:47+00:00

That would be amazing. I'm putting that on my 'things to explore with machine learning when I finally get into that space' list.

smrk007 | karma 93 | avg karma 1.6 · | 2018-06-27 00:33:35

Does anyone know if there is work similar to this being applied to machine learning? It seems like there could be a lot of potential.

ivan_ah | karma 5076 | avg karma 2.86 · | 2020-09-30 04:24:16

sci-map sounds very interesting. Have you looked at metacademy.org before? They did a lot of good work on the data model (concepts, resources, learning pathways, etc), and also collected a lot of content, mostly on computer topics. https://metacademy.org/graphs/concepts/bayesian_logistic_reg...

Sadly the project is no longer actively developed but if you haven't seen it yet, you should definitely check out for inspiration: https://github.com/metacademy

reply

jeremyarussell | karma 337 | avg karma 1.34 · | 2011-10-27 17:38:29+00:00

Tell me about it, Khan Academy helped a bit there but it's nice seeing this kind of stuff. Sometimes seeing it written out in text makes things click.

Thanks Allen Downey for the post.

Side note: I can't wait to see how the homework went. Machine Learning is pretty interesting so far.

reply

Y7ZCQtNo39 | karma 392 | avg karma 2.5 · | 2017-11-01 21:01:06+00:00

Looks like a great machine learning problem.

mlspector | karma 7 | avg karma 0.88 · | 2019-06-15 21:38:56+00:00

You might be interested in OpenReview, which is doing something like this, mainly in the ML/AI academic community.

(Disclaimer: I’m one of the developers)

https://openreview.net

reply

notgood | karma 729 | avg karma 2.95 · | 2016-11-10 01:16:47

You mean this script? Or machine learning in general? If the later then it has already been done: https://www.youtube.com/watch?v=qv6UVOQ0F44 (great educational video)

dorian-graph | karma 1145 | avg karma 1.91 · | 2016-06-23 02:44:30+00:00

I'm a big fan of this website in general, and they have a specific guide for 'everyone interested in machine learning'.

https://www.metacademy.org/roadmaps/cjrd/level-up-your-ml

reply

rayalez | karma 4393 | avg karma 4.69 · | 2016-10-15 10:45:43

There's a very interesting project:

https://metacademy.org

"Your package manager for knowledge".

(mostly focused around ML)

reply

stared | karma 9617 | avg karma 4.03 · | 2019-03-05 12:24:45

At some risk of hijacking the thread, some time ago I created a collaborative list of interactive machine learning examples: https://p.migdal.pl/interactive-machine-learning-list/ (repo: https://github.com/stared/interactive-machine-learning-list).