... in a piece I wrote about the Netflix Prize ten years ago, where I attempted to explain Singular Value Decomposition to NYT readers.
-
-
Replying to @pomeranian99 @alexismadrigal
Here's my 10-year-old Netflix Prize piece where I try to explain singular value decomposition to Wired readershttps://www.wired.com/2008/02/mf-netflix/ …
3 replies 4 retweets 25 likes -
I think gradient descent would be substantially easier than SVD actually!
1 reply 0 retweets 4 likes -
I can explain gradient descent even to non-math folks but lots of hand-waving of diff kind: to demonstrate. Harder to write in flat words.
2 replies 0 retweets 5 likes -
True -- there's something about flat words that makes this stuff hard. Visuals, animations, interactives, feel like they'd help a lot ...
1 reply 0 retweets 1 like -
Yep. Like this page could be much better with animations. :-) Much of this is all about navigating a (huuge) space.http://machinelearningmastery.com/gradient-descent-for-machine-learning/ …
1 reply 0 retweets 7 likes -
Replying to @zeynep @pomeranian99 and
Also am going to learn/do hands on machine learning stuff this summer. Really looking forward to playing with it but also to better explain.
2 replies 0 retweets 8 likes -
Replying to @zeynep @pomeranian99 and
Awesome. If any of you would like to read any of the Fast Forward Labs reports on emerging ML algorithms, please let me know!
3 replies 0 retweets 19 likes -
hey wait can i intern with you guys. haha
-
-
Replying to @zeynep @pomeranian99 and
haha hell yes. Come hang out anytime.
1 reply 0 retweets 5 likes -
Replying to @hmason @pomeranian99 and
i am not kidding so great.
will ping soon.2 replies 0 retweets 2 likes - Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.