Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
Blokirali ste korisnika/cu @ZeyuanAllenZhu
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @ZeyuanAllenZhu
-
Prikvačeni tweet
Is deep learning is actually performing DEEP learning? We may have given the first proof that neural network is capable of efficient hierarchical learning, while existing theory only shows that deep learning can "simulate" non-hierarchical algorithmshttps://twitter.com/MSFTResearch/status/1217198142229102593 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
V100 GPU is perhaps best for deep learning, but Azure has no V100 available throughout the United States for at least a week... Thoughts?
@AzureSupport@MSFTResearch@kevin_scott (also spent multiple days with support to investigate, so far no useful reply)Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
+ get FREE job title upgrade. From this year on, our intro-63-level titles become "Senior Researcher"https://twitter.com/ilyaraz2/status/1192134223194255361 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Zeyuan Allen-Zhu proslijedio/la je Tweet
ML and Optimization
@MSFTResearch @ Redmond is hiring researchers and postdocs! If you want to join@ZeyuanAllenZhu@SebastienBubeck Ofer Dekel@suriyagnskr Yin Tat Lee@jerryzli@ilyaraz2 Lin Xiao and several brilliant engineers, apply via below links by 12/31 (soft). Plz RT!
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Zeyuan Allen-Zhu proslijedio/la je Tweet
Overparametrization can be helpful for *unsupervised* learning, in unexpected ways! (e.g. latent variable recovery). Joint w/ Rares Buhai, Yoni Halpern and
@david_sontag.https://twitter.com/david_sontag/status/1145926998621134849 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Version 2 uploaded. Now, we have eliminated *all* kernel methods, in particular eliminated Convolution NTK with global average pooling.
https://twitter.com/MSFTResearch/status/1138129085207461888 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Zeyuan Allen-Zhu proslijedio/la je Tweet
I started a blog (https://kamathematics.wordpress.com/ )! I'll probably cross-link most posts here. Glad to finally get a chance to use the pun Ka-Math somehow. Still trying to procure a k@math.blahblah email address...
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Zeyuan Allen-Zhu proslijedio/la je Tweet
.
@deepcohen and@zicokolter realized that convolving a neural network with a Gaussian makes it robust against adversarial attacks. After lots of grind by@hadisalmanX and@TheGregYang, we improved their results by a lot using adversarial training by@aleks_madry and friends.https://twitter.com/TheGregYang/status/1139205510475833346 …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Zeyuan Allen-Zhu proslijedio/la je Tweet
Want generative models for *certifiably*
#fair data that can learn from biased samples? Try our new approach based on the max-entropy framework (with@profelisacelis). https://arxiv.org/abs/1906.02164 Bonus: fast algorithm for max-entropy inspired by@ZeyuanAllenZhu@aleks_madry et alHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
So, what do researchers do on Twitter?
#myfirstTweetHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

