Data Science

@opendatascience Нравится 0
Это ваш канал? Подтвердите владение для дополнительных возможностей

First Telegram Data Science channel. Covering all technical and popular staff about anything related to Data Science: AI, Big Data, Machine Learning, Statistics, general Math and the applications of former. For editors contact: @opendatasciencebot
Гео и язык канала
не указан, Английский
Категория
Технологии


Гео канала
не указан
Язык канала
Английский
Категория
Технологии
Добавлен в индекс
11.10.2017 07:05
реклама
TGAlertsBot
Мониторинг упоминаний ключевых слов в каналах и чатах.
SearcheeBot
Ваш гид в мире Telegram-каналов
Telegram Analytics
Подписывайся, чтобы быть в курсе новостей TGStat.
22 267
подписчиков
~7.3k
охват 1 публикации
~12.1k
дневной охват
~2
постов / день
32.9%
ERR %
1.65
индекс цитирования
Репосты и упоминания канала
11 упоминаний канала
0 упоминаний публикаций
66 репостов
Machinelearning
Machinelearning
Prelude to Space
Just links
uDatagram
Нейронач
Нейронач
CompBio
CompBio
Sokol_log
Нейронач
Physics Blues
Нейронач
CompBio
CompBio
Main ML_KZ
Science Doge
Science Doge
Main ML_KZ
Нейронач
Нейронач
Нейронач
Main ML_KZ
Нейронач
Science Doge
Just links
Нейронач
Just links
Science Doge
CompBio
CompBio
Deep Learning
Нейронач
Deep Learning
Deep Learning
Deep Learning
Science Doge
Science Doge
Loss function porn
Нейронач
My Way To Deep Learning
Нейронач
Anscombe's Quartet
Архивач
Science Doge
Каналы, которые цитирует @opendatascience
Loss function porn
Opensource Findings
Machinelearning
Loss function porn
Machinelearning
ML Тренировки
Loss function porn
Hacker News
EarthML
Power of data
Power of data
Loss function porn
Just links
Loss function porn
Loss function porn
Последние публикации
Удалённые
С упоминаниями
Репосты
Data Science 21 Aug, 20:48
ODS breakfast in Paris!

Free, open english-speaking casual meeting for anyone related to data science.

See you this Saturday at 10:30 at Malongo Café, 50 Rue Saint-André des Arts.
Data Science 21 Aug, 18:50
GPT-2: 6-Month Follow-Up

#OpenAI released the 774 million parameter #GPT2 language model.

Link: https://openai.com/blog/gpt-2-6-month-follow-up/

#NLU #NLP
🔥 26
😑 9
Data Science 21 Aug, 00:06
If you happen to be in Moscow in the next couple of weeks, we invite you to take part in Moscow Data Science Major on August 31st at Mail.ru Group office!

It’s like OpenDataScience’s Data Fest, but a mini version (in terms of duration, not content density). It’s like 1st of October, but 31st of August.

MDSM gather all researchers, engineers and developers around Data Science and Machine Learning:
- Top speakers and talks, zero bullshit
- Lots of new insights, skills and know-hows
- Best networking with the community

Link: https://datafest.ru/major/
Registration link: https://corp.mail.ru/ru/press/events/mdsm_aug19/
Читать полностью
Data Science 16 Aug, 15:24
Data Science 15 Aug, 13:11
​​🥇Parameter optimization in neural networks.

Play with three interactive visualizations and develop your intuition for optimizing model parameters.

Link: https://www.deeplearning.ai/ai-notes/optimization/

#interactive #demo #optimization #parameteroptimization #novice #entrylevel #beginner #goldcontent #nn #neuralnetwork
🥇 69
💩 4
Читать полностью
Data Science 14 Aug, 14:29
ODS breakfast in Paris! See you this Saturday at 10:30 at Malongo Café, 50 Rue Saint-André des Arts.
Data Science 14 Aug, 11:05
Neural Text d̶e̶Generation with Unlikelihood Training

Introducing a new objective, unlikelihood training, which forces unlikely generations to be assigned lower probability by the model, which improves overall quality of generated text.

Link: https://arxiv.org/pdf/1908.04319.pdf

#NLU #NLP #textgeneration
🧐 32
🤓 13
Data Science 13 Aug, 19:49
DeepMind's Behaviour Suite for Reinforcement Learning

DeepMind released Behaviour Suite for Reinforcement Learning, or ‘bsuite’ – a collection of carefully-designed experiments that investigate core capabilities of RL agents.

bsuite was built to do two things:

1. Offer clear, informative, and scalable experiments that capture key issues in RL
2. Study agent behaviour through performance on shared benchmarks

GitHub: https://github.com/deepmind/bsuite
Paper: https://arxiv.org/abs/1908.03568v1
Google colab: https://colab.research.google.com/drive/1rU20zJ281sZuMD1DHbsODFr1DbASL0RH

#RL #DeepMind #Bsuite
Читать полностью
Data Science 13 Aug, 17:35
Community Day @ MLSS 2019

MLSS Community Day is a free one-day event for everyone interested in Machine Learning.

Speakers from premier institutions in Machine Learning such as the University of Oxford, University College London, Max Planck Institute as well as renowned companies will cover the latest advances in applications for healthcare, telecommunications, NLP, finance, and quantum computing.

When & Where: August 31, Skoltech, Moscow
Link: https://mlss2019.skoltech.ru/community-day

#MLSS #MLSS2019 #Skolkovo
Читать полностью
Data Science 13 Aug, 13:24
Репост из: Loss function porn
T-shirt to inject junk data into surveillance systems. Stylish tool for peaceful protest against state human tracking
🔎 adversarialfashion.com
📉 @loss_function_porn
Data Science 12 Aug, 22:10
Репост из: Opensource Findings
​​Simple real time visualisation of the execution of a #python program: https://github.com/alexmojaki/heartrate
Data Science 12 Aug, 11:40
Репост из: Machinelearning
🔥 New Releases: PyTorch 1.2, torchtext 0.4, torchaudio 0.3, and torchvision 0.4

https://pytorch.org/blog/pytorch-1.2-and-domain-api-release/

https://github.com/pytorch/pytorch/releases
Data Science 12 Aug, 11:25
A Guide for Making Black Box Models Explainable.

One of the biggest challenges is to make ML models interpretable (explainable to human, preferably, non-expert). It matters not only in terms of credit scoring, to exclude possibility of racism or any other bias or news promotion and display (Cambridge Analytica case), but even in terms of debug and further progress in model training.


Link: https://christophm.github.io/interpretable-ml-book/

#guide #interpretablelearning #IL
🤓 20
🤖 5
Читать полностью
Data Science 8 Aug, 18:28
​​Unified rational protein engineering with sequence-only deep representation learning

UniRep predicts amino-acid sequences that form stable bonds. In industry, that’s vital for determining the production yields, reaction rates, and shelf life of protein-based products.

Link: https://www.biorxiv.org/content/10.1101/589333v1.full

#biolearning #rnn #Harvard #sequence #protein
Читать полностью
Data Science 8 Aug, 12:06
​​Photo to anime portrait

U-GAT-IT — Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation.

Link: https://github.com/taki0112/UGATIT

#Tensorflow #GAN #CV #DL #anime
🔥 117
😑 11
Data Science 8 Aug, 11:21
You do not need any presentation or preparation, this is free format for people who are around these days and wanna chat with fellow data scientists
Data Science 7 Aug, 22:11
ODS breakfast in Paris! See you this Saturday at 10:30 at Malongo Café, 50 Rue Saint-André des Arts.
Data Science 7 Aug, 12:27
spaCy meets PyTorch-Transformers: Fine-tune BERT, XLNet and GPT-2

Including pretrained models.

Link: https://explosion.ai/blog/spacy-pytorch-transformers
Pip: pip install spacy-pytorch-transformers

#Transformers #SpaCy #NLP #NLU #PyTorch #Bert #XLNet #GPT
Data Science 7 Aug, 11:51
PyTorch for research

PyTorch Lightning — The PyTorch Keras for ML researchers. More control. Less boilerplate.

Github: https://github.com/williamFalcon/pytorch-lightning

#PyTorch #Research #OpenSource
🌚 14
🌝 13
Data Science 7 Aug, 11:49
​​Long-form question answering

Facebook AI shared the first large-scale data set, code, and baseline models for long-form QA, which requires machines to provide long, complex answers — something that existing algorithms have not been challenged to do before.

Link: https://ai.facebook.com/blog/longform-qa/

#FacebookAI #Facebook #NLP #NLU #QA
🔥 33
😑 3
Читать полностью