SingleShotDetection, AnchorBoxes, RCNN and lots of finetuning tricks, all with code, slides and video. Courtesy of Mu Li https://t.co/qmvUTcjYBv
— Alex Smola (@smolix) April 10, 2019
SingleShotDetection, AnchorBoxes, RCNN and lots of finetuning tricks, all with code, slides and video. Courtesy of Mu Li https://t.co/qmvUTcjYBv
— Alex Smola (@smolix) April 10, 2019
From Variational to Deterministic Autoencoders
— hardmaru (@hardmaru) April 10, 2019
They show that simple regularized autoencoders can also learn a smooth, meaningful latent space without having to force the bottleneck code to conform to some arbitrarily chosen prior (ie Gaussian for VAEs).https://t.co/rsmiXk8Vw6
Ideas for building data ethics into culture:
— Rachel Thomas (@math_rachel) April 10, 2019
- Empower individuals to stop the process (andon cord)
- Anyone should be able to escalate issues
- Have an ethical challenge as part of hiring process
- Product reviews must ask questions about impact
- Have a diverse team pic.twitter.com/O1RofYgaWt
Aroma: code-to-code search and recommendation system from Facebook AI. https://t.co/Ix2TXDgqES
— Yann LeCun (@ylecun) April 9, 2019
In this week's #tidytuesday screencast, I analyze winners of Grand Slam tennis tournaments since 1968 🎾
— David Robinson (@drob) April 9, 2019
Don't miss my attempt to predict tournament winners based on a player's average past performance https://t.co/VIi3HUgOLD #rstats pic.twitter.com/V0uENpuL8w
Open Questions about Generative Adversarial Networks — A new Distill article by @gstsdn.https://t.co/eD5ShfiZAR
— distillpub (@distillpub) April 9, 2019
This is a great post that highlights the connection between the building blocks used in Transformers and Capsule Networks. Definitely worth reading! https://t.co/VsdzvxY4hN
— Sebastian Ruder (@seb_ruder) April 9, 2019
Unsupervised RNNGs (https://t.co/p80QaM7Rt6 from Yoon + DeepMind #naacl2019).
— harvardnlp (@harvardnlp) April 9, 2019
Learn a language model while jointly inducing syntactic structure. Exploits a constrained model (cfg-crf) for posterior approx in AVI.
(Neat to see grammar induction return🌴, e.g. PRPN, DIORA, ...) pic.twitter.com/CHzLyGtmu1
#rstats {hrbrthemes} 📦 just added `theme_ipsum_pub()` which uses the #spiffy Public Sans font (https://t.co/KlQFEQgF0Y) from the @USWDS.
— boB 🇷udis (@hrbrmstr) April 9, 2019
Tis in dev-mode on all the usual social coding suspects.
Windows testing 🙏🏽 as font names can be diff there & I dislike booting legacy OSes pic.twitter.com/sV9rF9R1wz
If you’re publishing a scatter plot, consider dividing it into quadrants using the medians https://t.co/3neJQse1VT
— Maarten Lambrechts (@maartenzam) April 9, 2019
MLIR is a new compiler framework designed to optimize the execution time of #machinelearning models and make it easier to add support for new devices to TensorFlow.
— TensorFlow (@TensorFlow) April 8, 2019
Check out this article to learn more → https://t.co/9hFRoScSnU
and our Github repo → https://t.co/lL8kuWdZpd pic.twitter.com/blSawHLc8Z
🃏 Double-down when you're down-and-out?
— Mara Averick (@dataandme) April 8, 2019
"Martingale strategies don't work, but we knew that - Simulation analysis in R" 🖋 @danoehm https://t.co/ZIMn7JD79y #rstats pic.twitter.com/VGAhWlBWfg