Glen Urban compares classical statistics with deep learning @mit_ide annual conferencepic.twitter.com/24Fs6kUvdM
Happiest when working on Random Forests from random beaches.
You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
Add this Tweet to your website by copying the code below. Learn more
Add this video to your website by copying the code below. Learn more
By embedding Twitter content in your website or app, you are agreeing to the Twitter Developer Agreement and Developer Policy.
| Country | Code | For customers of |
|---|---|---|
| United States | 40404 | (any) |
| Canada | 21212 | (any) |
| United Kingdom | 86444 | Vodafone, Orange, 3, O2 |
| Brazil | 40404 | Nextel, TIM |
| Haiti | 40404 | Digicel, Voila |
| Ireland | 51210 | Vodafone, O2 |
| India | 53000 | Bharti Airtel, Videocon, Reliance |
| Indonesia | 89887 | AXIS, 3, Telkomsel, Indosat, XL Axiata |
| Italy | 4880804 | Wind |
| 3424486444 | Vodafone | |
| » See SMS short codes for other countries | ||
This timeline is where you’ll spend most of your time, getting instant updates about what matters to you.
Hover over the profile pic and click the Following button to unfollow any account.
When you see a Tweet you love, tap the heart — it lets the person who wrote it know you shared the love.
The fastest way to share someone else’s Tweet with your followers is with a Retweet. Tap the icon to send it instantly.
Add your thoughts about any Tweet with a Reply. Find a topic you’re passionate about, and jump right in.
Get instant insight into what people are talking about now.
Follow more accounts to get instant updates about topics you care about.
See the latest conversations about any topic instantly.
Catch up instantly on the best stories happening as they unfold.
Glen Urban compares classical statistics with deep learning @mit_ide annual conferencepic.twitter.com/24Fs6kUvdM
Ugh. Are we still not past this?
What is wrong with the slide? Most statisticians I know are still shocked when they hear about how deep learning works. Pretty different paradigm, despite the same underpinning.
Lack of nuance. Tired over-generalizations. False dichotomy b/w "interpretable" and "accurate". Lack of awareness of transfer learning. Much the same stuff Breiman comprehensively knocked down decades ago https://projecteuclid.org/euclid.ss/1009213726 …
I think the stuff in this slide is what an earlier generation of folks widely believes - but I find when I show how scalable deep learning is to small datasets, how it can incorporate priors, how interpretable it can be, etc that they're *really* surprised!
What's your favorite small-dataset DL architecture/example/exercise? I'd love to try reproducing it inhttps://github.com/stripe/rainier
Also, I'm curious if you think the (very different) set of comparisons here is more fair (and if I'm saying something wrong or making an over-broad generalization, please let me know)https://github.com/stripe/rainier/blob/master/docs/dl.md …
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.