Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @zicokolter
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @zicokolter
-
Prikvačeni tweet
Excited to announce a collaboration between CMU and the Bosch Center for AI (BCAI). I'm joining BCAI as chief scientist of AI research, and they are funding my CMU group (where I'm remaining full time). Press release: https://www.businesswire.com/news/home/20180627005730/en/Bosch-Center-Artificial-Intelligence-establishes-research-lab … My comments:http://zicokolter.com/bosch/
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Zico Kolter proslijedio/la je Tweet
I am extremely excited to join the Artificial Intelligence lab
@Bosch_AI and@zicokolter team! I am looking forward towards new challenges and opportunities! 2 years with M*Modal (also as a part of@3MHISNews) were good and productive, but it's time for new adventures!Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Zico Kolter proslijedio/la je Tweet
When I invented adversarial training as a defense against adversarial examples, I focused on making it as cheap and scalable as possible. Eric and collaborators have now upgraded the original cheap version to compete with newer, more expensive versions.https://twitter.com/RICEric22/status/1217459930954981376 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Zico Kolter proslijedio/la je Tweet
Excited to hear from our confirmed speakers
@lujobauer Seeta Peña Gangadharan@timnitGebru@zicokolter at our upcoming ICLR workshop on trustworthy ML! Submit your work and join us on April 26 in Addis Ababa: http://trustworthyiclr20.github.io Deadline Jan 31 AoEhttps://twitter.com/NicolasPapernot/status/1219422530961924096 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Zico Kolter proslijedio/la je Tweet
1/ New paper on an old topic: turns out, FGSM works as well as PGD for adversarial training!* *Just avoid catastrophic overfitting, as seen in picture Paper: https://arxiv.org/abs/2001.03994 Code: https://github.com/locuslab/fast_adversarial … Joint work with
@_leslierice and@zicokolter to be at#ICLR2020pic.twitter.com/2EmwFaX7Qp
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Zico Kolter proslijedio/la je Tweet
Kolter's Team Wins First Place on Kaggle Competition with Over 2700 Teams Learn more → https://mld.ai/d3f5
#machinelearning#kaggle#research#ml#datasets cc:@shaojieb@zicokolter@csdatcmu@scsatcmuHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Zico Kolter proslijedio/la je Tweet
Congrats to the winners of the Outstanding New Directions Paper Award at
#NeurIPS2019:@zicokolter, chief scientist of#AI research at@Bosch_AI, and@_vaishnavh, PhD student at Carnegie Mellon University!
More: http://bit.ly/AIResearch_Bosch …pic.twitter.com/Zh1M9eXbp6
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Zico Kolter proslijedio/la je Tweet
Congrats to our winners of the Outstanding New Directions Paper Award at @NeurIPS2019 –
@_vaishnavh &@zicokolter from CMU and#BCAI. Find the download of the full paper “Uniform Convergence may be unable to explain generalization in Deep Learning” here: https://bit.ly/38cFNzn pic.twitter.com/kK06IFnfb7
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Come to
@_vaishnavh’s#NeurIPS2019 talk at 10:05 on uniform convergence, in expo hall C! Then run over to@shaojieb’s spotlight on deep equilibrium models at 10:40 in Ballroom C! My two PhD students with spotlights/orals are in different tracks in the same time slot naturally
.Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
#NeurIPS2019 registration line, 7am alternate version...pic.twitter.com/6QMVtEGdeV
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Naturally it wouldn’t be an excited tweet without a typo: talk of course is on 12/10 at 10:05.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Zico Kolter proslijedio/la je Tweet
Thrilled that our paper w/
@zicokolter on generalization in deep learning has been selected for the Outstanding New Directions Paper Award at#NeurIPS2019. Extremely grateful to the selection committee, reviewers & many others who provided useful feedback to improve our paper.https://twitter.com/hugo_larochelle/status/1203727951562338304 …Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Congrats to
@_vaishnavh for winning the Outstanding New Directions Paper Award at#NeurIPS2019! Come see his talk this Tuesday, 9/10, at 10:05am in West Exhibition Hall C + B3. Paper available here: https://arxiv.org/abs/1902.04742 https://twitter.com/_vaishnavh/status/1203839716899966977 …Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Excited to release our recent paper and library: easily optimize custom performance metrics (including constrained versions) using deep networks. Paper: https://arxiv.org/abs/1912.00965 Code: https://github.com/rizalzaf/ap_perf_py …https://twitter.com/rizalzaf/status/1201915202293436417 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Zico Kolter proslijedio/la je Tweet
This is cool! Instead of generic SGD, optimization layers represent the optimization of convex optimization problems directly: and the solution is itself differentiable.
@brandondamos https://www.cvxpy.org/ pic.twitter.com/QvmHSYmClQ
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Zico Kolter proslijedio/la je Tweet
Here's a 3 min video summary of our NeurIPS '19 oral paper on the generalization puzzle in deep learning.
@zicokolterhttps://www.youtube.com/watch?v=o3GfnEjTdIQ …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Zico Kolter proslijedio/la je Tweet
Take a glimpse at what happened at this year’s
#AICON19 hosted by the Bosch Center for AI and Cyber Valley#Bosch#ArtificialIntelligencepic.twitter.com/5hJKQOSk5SHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Zico Kolter proslijedio/la je Tweet
CVXPY is now differentiable. Try our PyTorch and TensorFlow layers using our package, cvxpylayers: https://github.com/cvxgrp/cvxpylayers … (& see our NeurIPS paper for details http://web.stanford.edu/~boyd/papers/pdf/diff_cvxpy.pdf …)
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Zico Kolter proslijedio/la je Tweet
Stoked to share a milestone project for all of us!
#NeurIPS2019 paper with@akshaykagrawal,@ShaneBarratt, S. Boyd, S. Diamond,@zicokolter: Differentiable Convex Optimization Layers Paper: http://web.stanford.edu/~boyd/papers/pdf/diff_cvxpy.pdf … Blog Post: https://locuslab.github.io/2019-10-28-cvxpylayers/ … Repo: https://github.com/cvxgrp/cvxpylayers …https://twitter.com/akshaykagrawal/status/1188845518962585600 …Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Zico Kolter proslijedio/la je Tweet
Excited to share my first paper with
@facebookai: The Differentiable Cross-Entropy Method with@denisyarats Paper: https://arxiv.org/abs/1909.12830 Videos: https://sites.google.com/view/diff-cross-entropy-method …pic.twitter.com/HefX4FUQ5k
Prikaži ovu nitHvala. 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.