#OpenDataScience community (ods.ai) recently released Open Machine Learning Course. This is a community-driven course, covering #production, #Kaggle (actually #CompetitiveDataScience, but we use this hashtag for the first time), #DL, #RL, #ML and validated on the russian-speaking DS community, which was translated into english.

There are lots of assignments and some competitions during the course. Interactive rating highly motivates and makes it fun to participate.

Next session starts on October 1. Welcome!

Link: https://mlcourse.ai?utm_source=telegram&utm_medium=opendatascience

#MIT recent release for video labeling

Youtube: https://www.youtube.com/watch?v=JBwSk6nJOyM&feature=youtu.be
Github: https://github.com/metalbubble/TRN-pytorch

#dl #video

You can also suggest any news, repo or post to our channel with @opendatasciencebot

You are welcome to share your open source work to request help, or just ask for starring it.

You are welcome to propose any post or article you want to.

Channel editors however will decide if that follows channel policy, which is OK for the majority of subscribers, judging by recent poll.

Thank you for your patience and constant forwards to friends! You do really matter, dear subscribers and the organic growth of this channel is the best reward.

“Software 2.0” last year, but still great article about what might happen in the future with the Software Development.
https://medium.com/@karpathy/software-2-0-a64152b37c35

Imposter Syndrome is a condition when person feels a liar, no matter what his/her achievements are. It is a great deal in the #DS too.

https://caitlinhudon.com/2018/01/19/imposter-syndrome-in-data-science

New library for #DataAugmentation: SOLT.

Supports various transformations for images, masks, targets and landmarks. Fast and easy-to-use library useful in #ComputerVision and #DeepLearning

Link: https://github.com/MIPT-Oulu/solt .

Paper «A Probabilistic U-Net for Segmentation of Ambiguous Images» from #NIPS2018 spotlight presentation.

Github: https://github.com/SimonKohl/probabilistic_unet
Github: Arxiv: https://arxiv.org/abs/1806.05034

#DeepMind #segmentation #cv

Deploying a Machine Learning Model as a REST API

Yet another #tutorial on how to serve #production model with flask.

Link: https://towardsdatascience.com/deploying-a-machine-learning-model-as-a-rest-api-4a03b865c166
Github repo: https://github.com/mnguyenngo/flask-rest-setup/tree/master/sentiment-clf

Deep learning application in classic and conservative area.

https://towardsdatascience.com/portfolio-optimization-with-deep-reinforcement-learning-2bcda07483b5


#moneytalking #dl #portfoliooptimization

AI Poker beat humans for the first time in two simultaneous-ish projects: DeepStack & Libratus, both of which use Counterfactual Regret Minimization. Good intro post for CRM, starting from Game Theory basics:

Blog: https://int8.io/counterfactual-regret-minimization-for-poker-ai/
Code: https://github.com/int8/counterfactual-regret-minimization

#rl #dl #poker

Data Hackers is a brazilian data science community and we've just released the first episode of our podcast. They reached out with the @opendatasciencebot saying that there're a lot of brazilians in our channel and it would be great to share this Portugese message:

Lançamos o podcast do Data Hackers. O primeiro episódio já está disponível no Spotify, Google Podcasts, iTunes, e muitas outras plataformas de streaming. Você também pode ouvir no post abaixo, além de saber um pouco mais sobre o projeto.

https://medium.com/data-hackers/confira-o-podcast-de-data-science-e-machine-learning-do-data-hackers-28d4659843b7

#GoogleAI ’s paper on highly-accurate genomes via #DeepLearning was published today in #NatureBiotech.

#DeepVariant is an analysis pipeline that uses a deep neural network to call genetic variants from next-generation DNA sequencing data.

Link: https://rdcu.be/7Dhl
Github: https://github.com/google/deepvariant

#infografics #CS #latency

Resilient Computing with Reinforcement Learning on a Dynamical System: Case Study in Sorting

RL agent learnt to sort using significantly fewer array manipulations than Quicksort.

Arxiv: https://arxiv.org/abs/1809.09261

Brilliant post on #CS and #Software about strategy and psychology of Software Development, which is highly applicable to Data Science too.

“Imaginary Problems Are the Root of Bad Software”

https://medium.com/s/story/imaginary-problems-d4f2921bd1b8

Top #Kaggle masters are releasing image augmentation library v0.1.1 with an extended bounding box support.

Guthub: https://github.com/albu/albumentations/releases/tag/v0.1.1

#cv #dl #dataaugmentation

Astrologers proclaimed month of #dataaugmentation since #GoogleAI released AutoAugment library — reinforcement learning algorithm which increases both the amount and diversity of existing data by finding optimal image augmentation policies.


Link: https://ai.googleblog.com/2018/06/improving-deep-learning-performance.html
Arxiv: https://arxiv.org/abs/1805.09501

Can Global Semantic Context Improve Neural Language Models?

New article by #Apple Frameworks Natural Language Processing Team

https://machinelearning.apple.com/2018/09/27/can-global-semantic-context-improve-neural-language-models.html

#nlp

Large scale GAN training for
high fidelity natural image synthesis

Link: https://openreview.net/pdf?id=B1xsqj09Fm
Samples: https://drive.google.com/drive/folders/1lWC6XEPD0LT5KUnPXeve_kWeY-FxH002

#gan #dl #cv