Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @ogrisel
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @ogrisel
-
Prikvačeni tweet
Slides and notebooks for the deep learning course
@CharlesOllion and I taught at@UnivParisSaclay https://m2dsupsdlclass.github.io/lectures-labs/ recsys vision nlpHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Olivier Grisel proslijedio/la je Tweet
Reminder: the neocognitron was published in 1979! https://twitter.com/rupspace/status/1224133745357099009 …pic.twitter.com/4wTQaXCX1P
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Olivier Grisel proslijedio/la je Tweet
Transformers 2.4.0 is out
- Training transformers from scratch is now supported
- New models, including *FlauBERT*, Dutch BERT, *UmBERTo*
- Revamped documentation
- First multi-modal model, MMBT from @facebookai, text & images Bye bye Python 2
https://github.com/huggingface/transformers/releases …Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Olivier Grisel proslijedio/la je Tweet
Did you know that Breiman published both the bagging and random forest papers *after* he retired?!? (This is from our forthcoming book: https://www.amazon.com/Deep-Learning-Coders-fastai-PyTorch/dp/1492045527 …)pic.twitter.com/07oAjxJgV3
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Olivier Grisel proslijedio/la je Tweet
Happy birthday
@scikit_learn !! Ten years from the first release and still young!pic.twitter.com/DXkTnoOdF9
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Olivier Grisel proslijedio/la je Tweet
Numba 0.48.0 has been released! This one comes shortly after 0.47.0 as we had many PRs that didn't make it in time. Quite a few bug fixes (including many CUDA fixes thanks to NVIDIA) and many new string methods contributed by Intel. More details:https://groups.google.com/a/continuum.io/forum/?utm_medium=email&utm_source=footer#!topic/numba-users/FkgzhvAA4lU …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Olivier Grisel proslijedio/la je Tweet
Pandas 1.0 is here! * Read the release notes: https://pandas.pydata.org/pandas-docs/version/1.0/whatsnew/v1.0.0.html … * Read the blogpost reflecting on what 1.0 means to our project: https://dev.pandas.io/pandas-blog/pandas-10.html … * Install with conda / PyPI: https://pandas.pydata.org/pandas-docs/version/1.0.0/getting_started/install.html … Thanks to our 300+ contributors to this release.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Olivier Grisel proslijedio/la je Tweet
Amazing work. PS: we're all so screwed.https://twitter.com/quocleix/status/1222268281932828672 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Olivier Grisel proslijedio/la je Tweet
10 PR already submitted and the first one just merged! Having fun at the Paris
@scikit_learn Sprint of the Decade!pic.twitter.com/OrUefbQ3hE
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
In the mean time the Quick and Simple Text Selection extensions is a good language agnostic workaround for list, dict, set and strings: https://marketplace.visualstudio.com/items?itemName=dbankier.vscode-quick-select …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
vscode-python users: please upvote the smart select support for Python code: https://github.com/microsoft/vscode-python/issues/6669 … . This would be helpful to refactor code without having to use the mouse to select structured code sections. Here is how it looks for Javascript code:https://code.visualstudio.com/updates/v1_35#_smart-selection-for-javascript-and-typescript …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Olivier Grisel proslijedio/la je Tweet
If you're interested in becoming involved in my new project dabl https://amueller.github.io/dabl/dev/ , I tagged some easy first issues. Given that it's pretty early in the development, the barrier to entry should hopefully be much lower than in sklearn for example: https://github.com/amueller/dabl/issues?q=is%3Aissue+is%3Aopen+sort%3Aupdated-desc+label%3A%22good+first+issue%22 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Olivier Grisel 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 -
Olivier Grisel proslijedio/la je Tweet
The quiet semisupervised revolution continueshttps://twitter.com/D_Berthelot_ML/status/1219823580654948353 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Olivier Grisel proslijedio/la je Tweet
Happy to share some of the work
@JovanVaex and I have been putting in@vaex_io to do#MachineLearning with@scikit_learn on 1 billion rows.#Python#DataScience#BigDatahttps://twitter.com/TDataScience/status/1220006212479209472 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Olivier Grisel proslijedio/la je Tweet
FixMatch: focusing on simplicity for semi-supervised learning and improving state of the art (CIFAR 94.9% with 250 labels, 88.6% with 40). https://arxiv.org/abs/2001.07685 Collaboration with Kihyuk Sohn,
@chunliang_tw@ZizhaoZhang Nicholas Carlini@ekindogus@Han_Zhang_@colinraffelpic.twitter.com/BmeYvpEHzX
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Olivier Grisel proslijedio/la je Tweet
This is a very interesting paper. It shows that a tweaked ResNet50 is about as accurate as EfficientNet-B4 but >3x faster. The EfficientNet paper measured FLOPS, which is a theoretical performance measure, rather than time, which is what actually matters. https://arxiv.org/abs/2001.06268 pic.twitter.com/cyBiueqPuf
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Olivier Grisel proslijedio/la je Tweet
Just in case anyone thinks that wind power forecasting is a solved problem: Here's the most recent UK national wind power forecast (in yellow) & actual (in red). That's a 4 GW error! More research definitely needed :) From https://www.bmreports.com/bmrs/?q=generation/windforcast/out-turn …pic.twitter.com/irvGIPtp0j
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Olivier Grisel proslijedio/la je Tweet
Thanks to *big* team effort, we released the code and the trained models from our LibriSpeech acoustic model architecture study and SOTA results https://arxiv.org/abs/1911.08460 herehttps://github.com/facebookresearch/wav2letter/tree/master/recipes/models/sota/2019 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Olivier Grisel proslijedio/la je Tweet
https://arxiv.org/abs/2001.04413 Cool theory paper presenting a problem that: - can be efficiently learned by SGD with a DenseNet with x^2 nonlin, - cannot be efficiently learned by any kernel method, including NTK.
Hvala. 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.