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

🎂🎉New Release - #Matplotlib 3.0.0. Supports Python 3. Highlights include:

GUI backend is selected at run-time based on what toolkits are installed;
New cyclic color map *twilight*;
Improvements to automatic layout of titles, ticks & GridSpec.

mail thread: https://mail.python.org/pipermail/matplotlib-announce/2018-September/000027.html
official site: https://matplotlib.org/users/whats_new.html
installation: pip install -U matplotlib

#visualization #dataviz

Introduction for machine learning for coders

Fast.ai launching new course for coders, having at least 1 year of experience. This is a practical-oriented course covering wide range of areas: classical Machine Learning with Random Forest and Gradient Decent, Regularization, NLP, Embeddings,

Link: https://www.fast.ai/2018/09/26/ml-launch/
Course itself: https://course.fast.ai/ml

#fastai #novice #entrylevel

AR Trajectory prediction

This is a real prototype with all the 30 lines of code to reimplement it.

Source: https://www.3delement.com/?p=610

#AR