Clojure numerical yak shave: provably efficient deep networks. Best mathy paper I've read lately. https://github.com/lynaghk/lorax /cc @_onionesque
-
-
Replying to @lynaghk
@lynaghk@_onionesque I've been meaning to implement that one. Will put it higher on the list.1 reply 0 retweets 0 likes -
Replying to @johnmyleswhite
@johnmyleswhite@_onionesque It's a cool algo. The author's implementation conflates test/train process, which took me a while to untangle.1 reply 0 retweets 0 likes -
Replying to @lynaghk
@lynaghk@_onionesque Early stopping style conflates? Or something worse?1 reply 0 retweets 0 likes
Replying to @johnmyleswhite
@johnmyleswhite @_onionesque Train/test are rows in same matrices; cannot just segment because you need to iterate entire matrix to inc dim
9:59 PM - 25 Jun 2013
0 replies
0 retweets
0 likes
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.