Register a SA Forums Account here!
JOINING THE SA FORUMS WILL REMOVE THIS BIG AD, THE ANNOYING UNDERLINED ADS, AND STUPID INTERSTITIAL ADS!!!

You can: log in, read the tech support FAQ, or request your lost password. This dumb message (and those ads) will appear on every screen until you register! Get rid of this crap by registering your own SA Forums Account and joining roughly 150,000 Goons, for the one-time price of $9.95! We charge money because it costs us money per month for bills, and since we don't believe in showing ads to our users, we try to make the money back through forum registrations.
 
  • Post
  • Reply
Lysidas
Jul 26, 2002

John Diefenbaker is a madman who thinks he's John Diefenbaker.
Pillbug
reverse the direction so instead of reducing dimensionality, it increases, like https://science.sciencemag.org/content/358/6364/793

(like the second half of a autoencoder)

Adbot
ADBOT LOVES YOU

Lysidas
Jul 26, 2002

John Diefenbaker is a madman who thinks he's John Diefenbaker.
Pillbug

ZZZorcerer posted:

I’ll try to get in the masters program at the CS department in my Uni later this year but another option that I was thinking was the Philosophy dept to try Law/Ethics in Computer/AI/ML :shobon:

just get a phd from CMU's ML department

Lysidas
Jul 26, 2002

John Diefenbaker is a madman who thinks he's John Diefenbaker.
Pillbug
ive gotten a lot of use out of cell ontology http://www.obofoundry.org/ontology/cl.html

Lysidas
Jul 26, 2002

John Diefenbaker is a madman who thinks he's John Diefenbaker.
Pillbug
and stochastic gradient descent sometimes takes you to a place thats even worse

Lysidas
Jul 26, 2002

John Diefenbaker is a madman who thinks he's John Diefenbaker.
Pillbug

qirex posted:

this is the entire industry, our whole product group got a "machine learning" mbo for the year

we do financial software, the one thing our clients don't want is unpredictable results, like they pay us millions of dollars to get only exactly what they want

just fit a l1 regularized logistic regression model to whatever they want, thats machine learning and is far more likely to give accurate results than whatever deep learning neural network stuff they probalby have in mind

Lysidas
Jul 26, 2002

John Diefenbaker is a madman who thinks he's John Diefenbaker.
Pillbug

stop

posting

Lysidas
Jul 26, 2002

John Diefenbaker is a madman who thinks he's John Diefenbaker.
Pillbug

BrokenGameboy posted:

Since the thread seems to mostly be talking about industry, what's ml been like in academia? Genuinely interested.

https://www.ml.cmu.edu/ is doing fantastically well

Adbot
ADBOT LOVES YOU

Lysidas
Jul 26, 2002

John Diefenbaker is a madman who thinks he's John Diefenbaker.
Pillbug
*points at logistic regression*

machine learning

  • 1
  • 2
  • 3
  • 4
  • 5
  • Post
  • Reply