Not quite machine learning, but close enough: method for calculating sqaure root inwardly.

DensePose: Dense Human Pose Estimation In The Wild

Facebook AI Research group presented a paper on pose estimation. That will help Facebook with better understanding of the processed videos.

NEW: DensePose-COCO, a large-scale ground-truth dataset with image-to-surface correspondences manually annotated on 50K COCO images.

Project website: http://densepose.org/
Arxiv: https://arxiv.org/abs/1802.00434

#facebook #fair #cvpr #cv #CNN #dataset

More papers are available at: https://research.fb.com/facebook-research-at-cvpr-2018/

Best paper award at #CVPR2018 main idea: study twenty five different visual tasks to understand how & when transfer learning works from one task to another, reducing demand for labelled data.

Video: https://youtu.be/SUq1CiX-KzM
Project website: http://taskonomy.stanford.edu
Arxiv: https://arxiv.org/pdf/1804.08328.pdf

How to Do Distributed Deep Learning for Object Detection Using Horovod on Azure

Link: https://blogs.technet.microsoft.com/machinelearning/2018/06/20/how-to-do-distributed-deep-learning-for-object-detection-using-horovod-on-azure/

#cloud #horovod #cv #dl

Another #CVPR2018 paper award: Global Pose Estimation with Attention-based RNNs.

Arxiv: https://arxiv.org/abs/1802.06857

#pose #rnn #dl

The natural language decathlon benchmark to do well on ten different nlp tasks including question answering, translation, summarization, sentiment analysis by Salesforce research team.

Project website: https://einstein.ai/research/the-natural-language-decathlon
PDF link: https://einstein.ai/static/images/pages/research/decaNLP/decaNLP.pdf
Github: https://github.com/salesforce/decaNLP

#nlp #dl

Microsoft Research announced Open Data project! This single, cloud-hosted location offers datasets representing many years of data curation and research efforts by Microsoft.

https://www.microsoft.com/en-us/research/blog/announcing-microsoft-research-open-data-datasets-by-microsoft-research-now-available-in-the-cloud/

#data #microsoft #opensource

Kaggle №1 Winning Approach for Plant Seedlings Classification


https://medium.com/@shridhar743/kaggle-1-winning-approach-for-image-classification-challenge-9c1188157a86

Results of the OpenAI's competition on reinforcement learning:
https://blog.openai.com/first-retro-contest-retrospective/

Hey guys (both male and female)! We are now 7157 and it’s time to find out a bit more about you.

Please, help the channel edition team to post more relivant information, by filling in the form:

https://goo.gl/forms/VBYApzVRGCUhzb713

A lil’ bit of interactive on @opendatascience: we updated the pre-last question with option «don’t remember».

And as a reminder: for those who want to suggest any news or posts, there is a special bot you can use to submit a post: @opendatasciencebot

80 responses / 1413 post views

Translating music to predict a musician’s body movements

Long story short: animating personalized avatar with the help of neural networks.

https://research.fb.com/translating-music-to-predict-a-musicians-body-movements/

#lstm #cvpr2018 #facebook

If you haven't already filled in the questionnaire, please complete it.

Now we are going to adjust the channel policy according to the responses, so opinion of 80 people will set it.

You can submit your responses to make YOUR opinion matter.

We will try to follow the requests of the auditory, but we need your responses.

3 min to complete: https://goo.gl/forms/VBYApzVRGCUhzb713

🔥🚀UPD2: Thank you! +50 responses in less than an hour!

UPD : 🔥💪135 people are making the future of this channel / 1545 views of the post with link.

And there are a lot of words of support, thank you, dear subscribers!

This is a day to remembered. #OpenAI 's team of five neural networks, OpenAI Five, has started to defeat amateur human teams (including a semi-pro team) at Dota 2:
https://blog.openai.com/openai-five/

It is important, because Dota2 is a way more complicated game than Chess or Go, where #AI has already surpassed human players.

#rl #reinforcementlearning #dl #dota2 #lstm

Tensorflow: The Confusing Parts (1)

The tutorial for beginners by Jacob, Google AI Resident. This can be nice intro for those, who wanted to get familiar with #TF

This is thorough introduction to the concepts underlying Tensorflow’s API; such as nodes, graphs and sessions.

https://jacobbuckman.com/post/tensorflow-the-confusing-parts-1/?utm_source=telegram&utm_medium=opendatascience

#tensorflow #tutorial #novice #beginner

Thank you all, folks, for support and suggestions, which you had sent through the questionnaire form.

You submitted 252 responses and our team now is able to know you better.

Most of you approve posting frequency and the content. We will continue to maintain the channel, especially after such warm approval!

Thank you, fellow Data Scientists.

Face recognition is now available as a JS-package with the help of face-api.js. It is built on top of #Tensorflow (js version).

https://itnext.io/face-api-js-javascript-api-for-face-recognition-in-the-browser-with-tensorflow-js-bcc2a6c4cf07?gi=a277ad002e2a

#cv #js #tf #dl #cnn

Automated Deep Reinforcement Learning Environment for Hardware of a Modular Legged Robot, from (sic!) Disney Research. They created configurable robots with an "env.reset()" that works on the real hardware enabling popular typical Gym-style ML directly on robots!

Link: https://www.disneyresearch.com/publication/automated-deep-reinforcement-learning-environment-for-hardware-of-a-modular-legged-robot/

#robo #rl #disney