Facebook, Carnegie Mellon build first AI that beats pros in 6-player poker
Main theoretical output: practical proof that carefully constructed AI algorithm can reach superhuman performance outside of two-player zero-sum games.
Training time: 8 days
Server: 64 core and 512 GB of RAM
Est. Cost to train: $150
The question whether that means end of the online poker, remains open for everyone to answer (or even try to train such bot themselves and take part).
Vote ๐ if you believe the industry won't notice.
Vote ๐ค if you believe that it will be affected.
Link: https://ai.facebook.com/blog/pluribus-first-ai-to-beat-pros-in-6-player-poker/
Main theoretical output: practical proof that carefully constructed AI algorithm can reach superhuman performance outside of two-player zero-sum games.
Training time: 8 days
Server: 64 core and 512 GB of RAM
Est. Cost to train: $150
The question whether that means end of the online poker, remains open for everyone to answer (or even try to train such bot themselves and take part).
Vote ๐ if you believe the industry won't notice.
Vote ๐ค if you believe that it will be affected.
Link: https://ai.facebook.com/blog/pluribus-first-ai-to-beat-pros-in-6-player-poker/
Meta
Facebook, Carnegie Mellon build first AI that beats pros in 6-player poker
Facebook AI and Carnegie Mellon researchers have built Pluribus, the first AI bot to beat top pros in six-player Texas Holdโem poker.
Alan Turing will become a face of new ยฃ50 note
That's a great acknowledgment of the man who stands behind most of the theoretical computing.
Link: https://www.bbc.com/news/business-48962557
Most famous Turing's work 'On computable numbers': https://www.cs.virginia.edu/~robins/Turing_Paper_1936.pdf
Turing machine: https://en.wikipedia.org/wiki/Turing_machine
#Turing #Theory #Math #history
That's a great acknowledgment of the man who stands behind most of the theoretical computing.
Link: https://www.bbc.com/news/business-48962557
Most famous Turing's work 'On computable numbers': https://www.cs.virginia.edu/~robins/Turing_Paper_1936.pdf
Turing machine: https://en.wikipedia.org/wiki/Turing_machine
#Turing #Theory #Math #history
Useful and practical post on pandas indexing
Link: https://www.shanelynn.ie/select-pandas-dataframe-rows-and-columns-using-iloc-loc-and-ix/
#beginner #pandas #practical #novice #entrylevel
Link: https://www.shanelynn.ie/select-pandas-dataframe-rows-and-columns-using-iloc-loc-and-ix/
#beginner #pandas #practical #novice #entrylevel
www.shanelynn.ie
Pandas iloc and loc โ quickly select data in DataFrames
The iloc, loc and ix indexers for Python Pandas select rows and columns from DataFrames. Simple guide to find data by position, label & conditional statements.
ODS breakfast in Berlin! See you this Wednesday at 08:30-10:00 at Einstein (Alexanderplatz 3, 10178 Berlin)
ODS Frรผhstรผck in Berlin! Wir sehen uns an diesem Mittwoch um 08:30 - 10:00 Uhr in Einstein cafe (Alexanderplatz 3, 10178 Berlin)
ODS Frรผhstรผck in Berlin! Wir sehen uns an diesem Mittwoch um 08:30 - 10:00 Uhr in Einstein cafe (Alexanderplatz 3, 10178 Berlin)
Should we create official chat for the channel to discuss links, answer common questions and to flood (during nighttime) ?
Anonymous Poll
26%
Yes (I will actively participate in the discussion)
35%
Yes (I will join and silently read)
20%
Yes (I will join and mute the chat, ocassionally reading conversations)
13%
I will not join
6%
Yes (I will join and volunteer to keep the chat and discussions clean and productive)
Large Memory Layers with Product Keys
Exploration of transformer architecture with special memory layer.
Link: https://arxiv.org/abs/1907.05242
#NLP #DL #transformer
Exploration of transformer architecture with special memory layer.
Link: https://arxiv.org/abs/1907.05242
#NLP #DL #transformer
arXiv.org
Large Memory Layers with Product Keys
This paper introduces a structured memory which can be easily integrated into a neural network. The memory is very large by design and significantly increases the capacity of the architecture, by...
Prisma founders launch Capture.
New app allows to take a photo of anything (even series and books) and get discuss it with random people online. All the processing is done on device. iOS only until autumn.
Link: https://techcrunch.com/2019/07/16/social-chat-app-capture-launches-to-take-a-shot-at-less-viral-success/
AppStore: https://apple.co/2xWnUUl
#Prisma #DL #CV #product
New app allows to take a photo of anything (even series and books) and get discuss it with random people online. All the processing is done on device. iOS only until autumn.
Link: https://techcrunch.com/2019/07/16/social-chat-app-capture-launches-to-take-a-shot-at-less-viral-success/
AppStore: https://apple.co/2xWnUUl
#Prisma #DL #CV #product
TechCrunch
Social chat app Capture launches to take a shot at less viral success
At first glance launching a new social app may seem as sensible a startup idea as plunging headfirst into shark-infested waters. But with even infamous curtain-ripper Facebook now making grand claims about a โpivot to privacyโ itโs clear something is shiftingโฆ
โโGenerative Modeling by Estimating Gradients of the Data Distribution
Paper on a different approach to generative modeling. We can estimate gradients of the data distribution and sample with Langevin dynamics. No adversarial method and no approximation for tractable training. Record-breaking inception score of 8.91 on CIFAR-10.
Github: https://github.com/ermongroup/ncsn
ArXiV: https://arxiv.org/abs/1907.05600
#GAN #CIFAR #cv #dl
Paper on a different approach to generative modeling. We can estimate gradients of the data distribution and sample with Langevin dynamics. No adversarial method and no approximation for tractable training. Record-breaking inception score of 8.91 on CIFAR-10.
Github: https://github.com/ermongroup/ncsn
ArXiV: https://arxiv.org/abs/1907.05600
#GAN #CIFAR #cv #dl
Data Science by ODS.ai ๐ฆ
Should we create official chat for the channel to discuss links, answer common questions and to flood (during nighttime) ?
We count every opinion and listen to your feedback, so please vote.
We also preparing special event for the chat creation, so stay tuned for the announcement
We also preparing special event for the chat creation, so stay tuned for the announcement
Microsoft open-sourced scripts and notebooks to pre-train and finetune BERT natural language model with domain-specific texts
Github: https://github.com/microsoft/AzureML-BERT
Earlier: https://t.me/opendatascience/837
#Bert #Microsoft #NLP #dl
Github: https://github.com/microsoft/AzureML-BERT
Earlier: https://t.me/opendatascience/837
#Bert #Microsoft #NLP #dl
GitHub
GitHub - microsoft/AzureML-BERT: End-to-End recipes for pre-training and fine-tuning BERT using Azure Machine Learning Service
End-to-End recipes for pre-training and fine-tuning BERT using Azure Machine Learning Service - microsoft/AzureML-BERT
Forwarded from Karim Iskakov - ะบะฐะฝะฐะป (Vladimir Ivashkin)
This media is not supported in your browser
VIEW IN TELEGRAM
I'd like to present our new paper with Yandex.Weather! We are pioneers in using a combination of satellite images, radar shots and neural networks for real-time rain forecast. Check out our video for more details!
โถ๏ธ youtu.be/9zd3VR-prYU
๐ yandex.com/weather/nowcast
๐ arxiv.org/abs/1905.09932
๐ @loss_function_porn
โถ๏ธ youtu.be/9zd3VR-prYU
๐ yandex.com/weather/nowcast
๐ arxiv.org/abs/1905.09932
๐ @loss_function_porn
ODS breakfast in Paris! See you this Saturday at 10:30 at Malongo Cafรฉ, 50 Rue Saint-Andrรฉ des Arts.
โโTabNine showed deep learning code autocomplete tool based on GPT-2 architecture.
Video demonstrates the concept. Hopefully, it will allow us to write code with less bugs, not more.
Link: https://tabnine.com/blog/deep
Something relatively similar by Microsoft: https://visualstudio.microsoft.com/ru/services/intellicode
#GPT2 #TabNine #autocomplete #product #NLP #NLU #codegeneration
Video demonstrates the concept. Hopefully, it will allow us to write code with less bugs, not more.
Link: https://tabnine.com/blog/deep
Something relatively similar by Microsoft: https://visualstudio.microsoft.com/ru/services/intellicode
#GPT2 #TabNine #autocomplete #product #NLP #NLU #codegeneration
Great collection of practical rules for routine DS engineering / research job.
Machine Learning in a company is 10% Data Science & 90% other challenges, this pdf provides a great deal of principals and solutions to deal with them.
We can only recommend saving this post to your Saved Messages by forwarding it to yourself.
Link: http://martin.zinkevich.org/rules_of_ml/rules_of_ml.pdf
#cheatsheet #advice #practical #common #shouldbesaved
Machine Learning in a company is 10% Data Science & 90% other challenges, this pdf provides a great deal of principals and solutions to deal with them.
We can only recommend saving this post to your Saved Messages by forwarding it to yourself.
Link: http://martin.zinkevich.org/rules_of_ml/rules_of_ml.pdf
#cheatsheet #advice #practical #common #shouldbesaved
โโYouTokenToMe, new tool for text tokenisation from VK team
Meet new enhanced tokenisation tool on steroids. Works 7-10 times faster alphabetic languages and 40 to 50 times faster on logographic languages, than alternatives.
Under the hood (watch source) there is C++ implementation with python bindings, using Byte Pair Encoding (BPE) algorithm. YouTokenToMe beats #SentencePiece by Google and #fastBPE, created by a researcher from Facebook AI Research in terms of speed.
Github: https://github.com/vkcom/YouTokenToMe
Medium: https://medium.com/@vktech/youtokentome-a-tool-for-quick-text-tokenization-from-the-vk-team-aa6341215c5a
Byte Pair Encoding: https://arxiv.org/abs/1508.07909
Meet new enhanced tokenisation tool on steroids. Works 7-10 times faster alphabetic languages and 40 to 50 times faster on logographic languages, than alternatives.
Under the hood (watch source) there is C++ implementation with python bindings, using Byte Pair Encoding (BPE) algorithm. YouTokenToMe beats #SentencePiece by Google and #fastBPE, created by a researcher from Facebook AI Research in terms of speed.
Github: https://github.com/vkcom/YouTokenToMe
Medium: https://medium.com/@vktech/youtokentome-a-tool-for-quick-text-tokenization-from-the-vk-team-aa6341215c5a
Byte Pair Encoding: https://arxiv.org/abs/1508.07909
Data Science by ODS.ai ๐ฆ
โโYouTokenToMe, new tool for text tokenisation from VK team Meet new enhanced tokenisation tool on steroids. Works 7-10 times faster alphabetic languages and 40 to 50 times faster on logographic languages, than alternatives. Under the hood (watch source)โฆ
This improvement for everyday used toolset deserves minimum 50 claps at Medium and a Star on github!
Letโs give VK research team appreciation from the community they deserve ๐!!
Letโs give VK research team appreciation from the community they deserve ๐!!
Whatโs wrong with transformer architecture: an overview
How the Transformers broke NLP leaderboards and why that can be bad for industry.
Link: https://hackingsemantics.xyz/2019/leaderboards/
#NLP #overview #transformer #BERT #XLNet
How the Transformers broke NLP leaderboards and why that can be bad for industry.
Link: https://hackingsemantics.xyz/2019/leaderboards/
#NLP #overview #transformer #BERT #XLNet
Hacking semantics
How the Transformers broke NLP leaderboards
With the huge Transformer-based models such as BERT, GPT-2, and XLNet, are we losing track of how the state-of-the-art performance is achieved?
โโSimultaneous food and facial recognition at a Foxconn factory canteen, Shenzhen China
#video #foodlearning #facerecogniction #dl #cv #foxconn
#video #foodlearning #facerecogniction #dl #cv #foxconn
โโDeep Learning Image Segmentation for Ecommerce Catalogue Visual Search
Microsoftโs article on image segmentation
Link: https://www.microsoft.com/developerblog/2018/04/18/deep-learning-image-segmentation-for-ecommerce-catalogue-visual-search/
#CV #DL #Segmentation #Microsoft
Microsoftโs article on image segmentation
Link: https://www.microsoft.com/developerblog/2018/04/18/deep-learning-image-segmentation-for-ecommerce-catalogue-visual-search/
#CV #DL #Segmentation #Microsoft
