52748
Twitter
RT : The 15 most deadly police departments in America. St. Louis is off the charts.
from twitter
5 hours ago
Twitter
RT : Please make trend. They’re 100% without power and can’t tweet it themselves. Unprecedented levels of as…
PuertoRico  from twitter
5 hours ago
Twitter
RT : When you get a work e-mail on the weekend.
from twitter
6 hours ago
Twitter
RT : Check out how is using and in their rewards program for frictionless proof-of-purchase!…
TensorFlow  AI  from twitter
9 hours ago
Merantix - Transforming the world with curious minds
We conceptualize, build, and scale AI ventures.

Merantix is a research lab and venture builder in the space of artificial intelligence. We help mid- to large-sized companies explore and leverage the potential of deep learning. We have a strong bias for partnerships with companies that have powerful data sets, and relatively short decision cycles. Consulting fees are not our main incentive. We are willing to take investment risks together with our venture partners.

We build partnerships with leading companies and organizations to assemble complex datasets and build machine learning solutions that address industries such as health, finance, automotive and advertising.
machine_learning 
10 hours ago
Twitter
RT : I think "threatening" is a bit of an understatement, given tape of Mitch McConnell saying "Koch Bros own us all."
from twitter
17 hours ago
Twitter
RT : See also: residents of the *U.S.* Virgin Islands.
from twitter
18 hours ago
Twitter
RT : Almost 3.5 million Americans will be without power for four to six months.
from twitter
yesterday
Twitter
RT : Happy news: I've joined Google, to work on making TensorFlow an even more successful open source project…
from twitter
yesterday
Twitter
RT : I appreciate James Damore continuing to provide evidence that the bar at Google was most certainly lowered in a spe…
from twitter
yesterday
Twitter
RT : The scariest thing about 2017’s hurricanes: They got really bad really fast via…
from twitter
yesterday
Azure/Machine-Learning-Operationalization: Deploying machine learning models to Azure
Deploying machine learning models to Azure

Operationalization is the process of publishing models and code as web services and the consumption of these services to produce business results.

Azure Machine Learning Operationalization is a component of the Azure CLI that enables operationalization of models that you create through Vienna that use the CNTK, SPARK, and Python machine learning platforms.
machine_learning  azure 
yesterday
terinjokes/StickerConstructorSpec: The Sticker Standard - hexagon sticker spec
This specifications defines the standard sizes and orientation to allow consistent sticker sizes between vendors. Allowing maximum enjoyment from receivers of stickers, and allow sticker companies to develop tools and interfaces for creating compliant stickers. This specification is also a definitive place to know what dimensions a sticker should be.
yesterday
[1704.05021] Sparse Communication for Distributed Gradient Descent
We make distributed stochastic gradient descent faster by exchanging sparse updates instead of dense updates. Gradient updates are positively skewed as most updates are near zero, so we map the 99% smallest updates (by absolute value) to zero then exchange sparse matrices. This method can be combined with quantization to further improve the compression. We explore different configurations and apply them to neural machine translation and MNIST image classification tasks. Most configurations work on MNIST, whereas different configurations reduce convergence rate on the more complex translation task. Our experiments show that we can achieve up to 49% speed up on MNIST and 22% on NMT without damaging the final accuracy or BLEU.

..goog has unpub'd paper on doing the same..
machine_learning 
yesterday
Twitter
RT : Hard to imagine the guy who did shady insider trading as a House member would get mixed up in corruption.
from twitter
yesterday
The free knowledge-sharing platform for technology
Tech.io is a collaborative platform to discover and share unique perspectives on any technology through open-source playgrounds. Empower others to learn by crafting hands-on tutorials on topics that matter to you.
yesterday
Twitter
RT : I'm hoping that I can successfully replicate my experiment and thus create reliable nanoparticles that can deliver…
from twitter
2 days ago
Twitter
RT : Bill is moving so fast, and without analysis, so sponsors can tell different untruths to different constituencies.
from twitter
2 days ago
Tyke
"Tyke is a macOS menu bar application I made because I really needed it."
(andre torrez)
osx 
2 days ago
[1611.04558v1] Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation
We propose a simple, elegant solution to use a single Neural Machine Translation (NMT) model to translate between multiple languages. Our solution requires no change in the model architecture from our base system but instead introduces an artificial token at the beginning of the input sentence to specify the required target language. The rest of the model, which includes encoder, decoder and attention, remains unchanged and is shared across all languages. Using a shared wordpiece vocabulary, our approach enables Multilingual NMT using a single model without any increase in parameters, which is significantly simpler than previous proposals for Multilingual NMT. Our method often improves the translation quality of all involved language pairs, even while keeping the total number of model parameters constant. On the WMT'14 benchmarks, a single multilingual model achieves comparable performance for English→French and surpasses state-of-the-art results for English→German. Similarly, a single multilingual model surpasses state-of-the-art results for French→English and German→English on WMT'14 and WMT'15 benchmarks respectively. On production corpora, multilingual models of up to twelve language pairs allow for better translation of many individual pairs. In addition to improving the translation quality of language pairs that the model was trained with, our models can also learn to perform implicit bridging between language pairs never seen explicitly during training, showing that transfer learning and zero-shot translation is possible for neural translation. Finally, we show analyses that hints at a universal interlingua representation in our models and show some interesting examples when mixing languages.
machine_learning  nlp 
2 days ago
Twitter
RT : Name's Benjamin Kwashie from Ghana. I draw with ballpoint pen.
drawingwhileblack  from twitter
2 days ago
Twitter
RT : WOW. Rohrabacher just straight-up said he's working against US intelligence agencies & accused NSA/FBI/CIA of lying…
from twitter
2 days ago
Twitter
RT : Draft report "was obtained by The New York Times." Some proponents believe it was suppressed...
from twitter
2 days ago
Twitter
RT : Word of the day: “glep-de-wadder” - a bright shard of rainbow at a distance from the sun (Shetland; Eshaness)
from twitter
2 days ago
« earlier      
#ebook #gov20 #opengov @bbcscitech @brainpicker @daringfireball @ebertchicago @glynmoody @greatdismal @jscarroll @medicalnews @mindhackz @neuraxon77 @newscientist @pkedrosky @smashingmag @stilgherrian academia ack activism aggregator ajax amazon amusements analysis analytics animals api apple arghh art astronomy audio austin australia aws bigdata bigquery biology blogging blogs books business cats charity chocolate civil_liberties climate climate_change clothing cloud_computing coffee cognition comment communication computing cool css culture data database dataflow datamining design development distributed ebook ebooks ec2 economics economy education email environment essays evolution extensions feminism finance firefox food framework from gadgets gae gce gcp geekery gender genetics geolocation git global_warming golang google gov20 graphics gwt hadoop hardware health heh history internet interviews ipad iphone iraq java javascript journalism k8s kansas kubernetes language law libraries mac machine_learning makerfaire mapreduce maps md media medicine mobile movies music my nature neuroscience news open_source opengov oscon osx pens philosophy photography photoshop php physics plugins politics presentations privacy productivity programming psychology python rails recipes reference religion research resources reviews rss ruby s3 scalability science search seattle security sent sex society software software/social statistics storage strataconf stuff sxsw sydney tagging tbr technology tensorflow texas tips tools travel tutorials tweets twitter twitter_fav typography uk usa utilities vegetarianism version_control videos visualizations war web_app web_design web_dev web_services wishlist wordpress world writers writing

Copy this bookmark:



description:


tags: