_______ __ _______
| | |.---.-..----.| |--..-----..----. | | |.-----..--.--.--..-----.
| || _ || __|| < | -__|| _| | || -__|| | | ||__ --|
|___|___||___._||____||__|__||_____||__| |__|____||_____||________||_____|
on Gopher (inofficial)
URI Visit Hacker News on the Web
COMMENT PAGE FOR:
URI A Visual Introduction to Machine Learning (2015)
jazzpush2 wrote 28 min ago:
Amazing. A very cool niche area, dataviz x ai/ml. See also:
- mlu-explain.github.io
- visxai.io
- google PAIR's explorables
- GA Tech's poloclub.
AlexDunit wrote 55 min ago:
Still one of the best explanations of decision trees I've seen. The
scroll-driven animation that builds the tree split by split, while
simultaneously showing where each data point lands, does in 30 seconds
what most textbook diagrams fail to do in three pages
davispeck wrote 2 hours 43 min ago:
The interactive explanations here are still some of the best examples
of how visualization can make ML concepts intuitive.
I wish more technical articles took this approach instead of starting
with equations.
vivzkestrel wrote 3 hours 47 min ago:
- A previous comment by me about my list of absolutely gorgeous,
interactive, animated, high dynamic learning resources classified as S
TIER
- S-TIER blogs are those that are animated, visual, interactive and
absolutely blow your mind off
- A-TIER are highly informative and you ll learn something
- opinion blogs at the absolute bottom of the tier list because
everyone everywhere ll always have an opinion about everything and my
life is too short to be reading all that
- these are the S-TIER ones on my system
- [1] - [2] - [3] - [4] - [5] - [6] - these are the BEST of the BEST,
you ll be blown away opening each page is how good they are. i am
thinking of creating a bookmark manager that uses my criteria above and
runs across every damn blog link ever posted on HN to categorize them
as S-TIER, A-TIER, opinion and so on
URI [1]: https://growingswe.com/blog
URI [2]: https://ciechanow.ski/archives/
URI [3]: https://mlu-explain.github.io/
URI [4]: https://seeing-theory.brown.edu/index.html#firstPage
URI [5]: https://svg-tutorial.com/
URI [6]: https://www.lumafield.com/scan-of-the-month/health-wearables
1wheel wrote 3 hours 9 min ago:
[1] has a bunch more too â see the Hall of Fame section at the
bottom for some of the highlights.
I also made a dozen of these a couple years ago, my two favorites:
- [2] -
URI [1]: https://visxai.io/
URI [2]: https://pair.withgoogle.com/explorables/fill-in-the-blank/
URI [3]: https://pair.withgoogle.com/explorables/grokking/
xpe wrote 4 hours 6 min ago:
The balls-from-the-sky sieve-style animation* showing classifications
literally falling out of the decision tree is my favorite part. I
haven't seen this anywhere else (yet); this visualization technique
deserves more percolation (pun intended). (#1)
Not even to mention the fact that the animation is controlled by
scrolling, which gives an intuitive control over play, pause, rewind,
fast-forward, etc. Elegant and brilliant. (#2)
Stunningly good also in the sense that it advances the story so people
don't just drool at the pretty animation and stop engaging. Thus
putting the "dark arts" in the service of learning. (#3)
All three ideas warrant emulation in other contexts!
* Find it towards the bottom under the "Making predictions" heading.
nullora wrote 4 hours 12 min ago:
nice
sp4cec0wb0y wrote 4 hours 14 min ago:
Did they not have mobile responsive sites in 2015? Lol
1wheel wrote 1 hour 45 min ago:
2015 was about the last year you could get away with publishing an
interactive graphic with a fixed width â this made it harder do
really creative/original work.
mvrckhckr wrote 4 hours 43 min ago:
This is still great after more than a decade.
tonyhschu wrote 5 hours 26 min ago:
One of the creators of R2D3 here. Funny to wake up to this today! Happy
to answer questions here or on bsky
Genbox wrote 3 hours 47 min ago:
If I would like to build a visualization like this, but for a data
ingestion pipeline, any tips on where to start?
I have it visually in my head, but it feels overwhelming getting it
into a website.
avabuildsdata wrote 1 hour 53 min ago:
fwiw I work on data ingestion pipelines and I've found that
starting with just boxes-and-arrows in something like Excalidraw
gets you 80% of the way to knowing what you actually want. The gap
between "I can picture it" and "I can build it on a webpage" is
mostly a d3 learning curve problem, not a design problem.
xyflow that the creator mentioned is probably the right call for
pipeline DAGs though -- we use it internally for visualizing our
scraping workflows and it was surprisingly painless to get running
tonyhschu wrote 2 hours 40 min ago:
Sort of like this? [1] I used [2] for this, with css animations for
the edges. Itâs probably easier now with coding agents and what
not
URI [1]: https://docs.tecton.ai/docs/introduction/interactive-tour
URI [2]: https://github.com/xyflow/xyflow
reader9274 wrote 3 hours 49 min ago:
Any plans for more articles, 10 years later?
quickrefio wrote 5 hours 44 min ago:
R2D3 did an amazing job here. Itâs rare to see statistical learning
concepts explained visually this clearly.
smaili__ wrote 6 hours 10 min ago:
So amazing, wish there were more articles like this. I love visual
learning.
Also reminds me of another blog post: [1] , probably not directly the
same, but similar-ish written blog posts, easy to stay on track and
follow. It is so easy to learn with this kind of blog post.
URI [1]: https://pomb.us/build-your-own-react/
stared wrote 6 hours 52 min ago:
It is a masterpiece! Each time I give an introduction to machine
learning, I use this explorable explanation.
There is a collection of a few more here:
URI [1]: https://p.migdal.pl/interactive-machine-learning-list/
kengoa wrote 2 hours 34 min ago:
Nice list! I remember HN talking about [1] when it came out but sadly
it seems like this website was discomissioned.
Added an entry for my data visualisation tool here: [2] .
Edit: found an updated link for seeing theory so I fixed it in the PR
above. Feel free to cherry-pick if #24 is not relevant.
URI [1]: https://students.brown.edu/seeing-theory/
URI [2]: https://github.com/stared/interactive-machine-learning-list/...
shardullavekar wrote 7 hours 28 min ago:
has anyone come across an r2d3-style explainer for something as
high-dimensional as a Transformer's attention mechanism?
lamename wrote 7 hours 22 min ago:
Not quite, but these help [1]
URI [1]: https://poloclub.github.io/transformer-explainer/
URI [2]: https://youtu.be/wjZofJX0v4M?si=gT8Zlz1IY14KV_ju
cake-rusk wrote 9 hours 13 min ago:
Where's the rest of it?
jojohack wrote 4 hours 53 min ago:
Part 2:
URI [1]: https://r2d3.us/visual-intro-to-machine-learning-part-2/
Jhater wrote 9 hours 53 min ago:
Josh Starmers books are very visual as well, probably the best source
I'd recommend to learn ML [1]
URI [1]: https://www.youtube.com/c/joshstarmer
URI [2]: https://statquest.org/
ayhanfuat wrote 10 hours 1 min ago:
This is from 2015. Both technically and conceptually it was ahead of
its time.
mdp2021 wrote 9 hours 5 min ago:
It's a pity there seems not to be new (or other) material from Tony
Hschu and Stephanie Jyee.
(Or can anybody find something more?)
DIR <- back to front page