​​💣New open-source recommender system from Facebook.

Facebook is open-sourcing DLRM — a state-of-the-art deep learning recommendation model to help AI researchers and the systems and hardware community develop new, more efficient ways to work with categorical data.

Link: https://ai.facebook.com/blog/dlrm-an-advanced-open-source-deep-learning-recommendation-model/
Github: https://github.com/facebookresearch/dlrm
ArXiV: https://arxiv.org/abs/1906.03109

#Facebook #DLRM #recommender #DL #PyTorch #Caffe

​​XLNet: Generalized Autoregressive Pretraining for Language Understanding

Researchers at Google Brain and Carnegie Mellon introduce #XLNet, a pre-training algorithm for natural language processing systems. It helps NLP models (in this case, based on Transformer-XL) achieve state-of-the-art results in 18 diverse language-understanding tasks including question answering and sentiment analysis.

Article: https://towardsdatascience.com/what-is-xlnet-and-why-it-outperforms-bert-8d8fce710335
ArXiV: https://arxiv.org/pdf/1906.08237.pdf

#Google #GoogleBrain #CMU #NLP #SOTA #DL

0.2 release of PyTorchPipe

Library for multi-modal deep learning pipelines, in a modular fashion for GPU and CPU.

Link: https://github.com/IBM/pytorchpipe

#IBM #PyTorch

Hey, fellow researchers, engineers and students.

We can recommend you another great frequently updated channel, covering Machine and Deep Learning: @ai_machinelearning_big_data

Videos from ICML 2019 conference

Link: https://icml.cc/Conferences/2019/Videos

#ICML2019 #video

Yet another good intro into difference between artificial neural network and biological one.

If you're getting started in Data Science, you need to start with the basic building building block of Neural Networks - a Perceptron. To understand what it is, there's this good link to get started with.

Link: https://towardsdatascience.com/the-differences-between-artificial-and-biological-neural-networks-a8b46db828b7

#nn #entrylevel #beginner

Github repo with collection of NLP articles with short description

Link: https://github.com/mihail911/nlp-library

#tldr #nlp #github #dl

​​Using AI to balance a card game on the example of Hearthstone

Hearthstone — complex CCG by Blizzard with hundreds of cards. Paper is about balancing the game through multiobjective evolutionary algorithms. Authors show how to rebalance the game while making minimal card changes.

Link: https://arxiv.org/abs/1907.01623

#AI #Blizzard #Hearthstone #balance #linearprogramming #ccg

🔥🎓New FastAI's free online course on NLP

It is called «A Code-First Introduction to Natural Language Processing». All code & videos are available for free online, make sure you save this link into bookmarks and at least review the content, because it provides opportunity not only to learn new skills, but to actually understand how NLP works.

Link: https://www.fast.ai/2019/07/08/fastai-nlp/

#NLP #NLU #DL #MOOC #FastAI #course

ODS breakfast in Paris! See you this Saturday at 10:30 at Malongo Café, 50 Rue Saint-André des Arts.

BlazeFace: Sub-millisecond Neural Face Detection on Mobile GPUs

Authors claim really fast face detection on mobile devices.

Link: https://arxiv.org/abs/1907.05047

#FaceRecognition #CV #mobile #DL

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 🃏 if you believe the industry won't notice.
Vote 🤖 if you believe that it will be affected.

Link: https://ai.facebook.com/blog/pluribus-first-ai-to-beat-pros-in-6-player-poker/

Alan Turing will become a face of new £50 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

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

ODS breakfast in Berlin! See you this Wednesday at 08:30-10:00 at Einstein (Alexanderplatz 3, 10178 Berlin)
ODS Frühstück in Berlin! Wir sehen uns an diesem Mittwoch um 08:30 - 10:00 Uhr in Einstein cafe (Alexanderplatz 3, 10178 Berlin)

Large Memory Layers with Product Keys

Exploration of transformer architecture with special memory layer.

Link: https://arxiv.org/abs/1907.05242

#NLP #DL #transformer

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

​​Generative 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

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

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://yangx.top/opendatascience/837

#Bert #Microsoft #NLP #dl