Data Science by ODS.ai 🦜

#DeepMind new release: Neural Processes (#NPs) that generalise #GQN ’s training regime to other few-shot prediction tasks such as regression and classification

Arxiv 1: https://arxiv.org/abs/1807.01622
Arxiv 2: https://arxiv.org/abs/1807.01613

#ICML2018

4.36K views14:21

How #Netflix used data science to make scripts for the shows:

Video: https://www.youtube.com/watch?v=qXo9jTxfqJ8&feature=youtu.be
Github: http://netflix.github.io

Really great video, showing practical approach, with some focus on human interactions and integrating data insights into the product.

#youtube #netflixresearch

YouTube

Netflix Data: From Script to Screen - Netflix Los Angeles - June 2017

Ever wonder how Netflix leverages data and analytics to influence the shows and content they create? Hear it straight from Netflix's LA-based content data team themselves. Netflix’s cast of data professionals share aspects of their processes and tools used…

👍1

4.31K views09:30

Data Science by ODS.ai 🦜

Udacity has published a github repo for the Deep Reinforcement Learning Nanodegree program

Repo: https://github.com/udacity/deep-reinforcement-learning
Nanodegree: https://www.udacity.com/course/deep-reinforcement-learning-nanodegree--nd893

#dl #udacity #mooc #course #github #rl

GitHub

GitHub - udacity/deep-reinforcement-learning: Repo for the Deep Reinforcement Learning Nanodegree program

Repo for the Deep Reinforcement Learning Nanodegree program - udacity/deep-reinforcement-learning

4.71K views09:33

Data Science by ODS.ai 🦜

Deep Learning for Matching in Search and Recommendation

PDF: http://www.comp.nus.edu.sg/~xiangnan/sigir18-deep.pdf

#sigir2018 #Tutorial

3.81K views15:29

Data Science by ODS.ai 🦜

Glow by #OpenAI: Better Reversible Generative Models

Project link: https://blog.openai.com/glow/
Video: https://d4mucfpksywv.cloudfront.net/research-covers/glow/videos/both_loop_new.mp4

Openai

Glow: Better reversible generative models

We introduce Glow, a reversible generative model which uses invertible 1x1 convolutions. It extends previous work on reversible generative models and simplifies the architecture. Our model can generate realistic high resolution images, supports efficient…

3.9K views18:31

Data Science by ODS.ai 🦜

4.56K views21:33

Data Science by ODS.ai 🦜

Dynamic few-shot visual learning without forgetting by Gidaris and Komodakis

The authors share even configs and learning rate schedules for experiments in paper.

Github: https://github.com/gidariss/FewShotWithoutForgetting

#cvpr2018

GitHub

GitHub - gidariss/FewShotWithoutForgetting

Contribute to gidariss/FewShotWithoutForgetting development by creating an account on GitHub.

3.85K views11:02

Data Science by ODS.ai 🦜

SwitchNorm: add BatchNorm + InstanceNorm + GroupNorm with a learnable blend at each layer.

Paper about optimal normalization in neural nets continues. Plots + code

Arxiv: https://arxiv.org/abs/1806.10779

#dl #normalization

4.02K views11:03

Data Science by ODS.ai 🦜

And it would be a crime to leave #ICML2018 out.

It is held in Stockholm now, papers are available at: http://proceedings.mlr.press/v80/

#conference

Proceedings of Machine Learning Research

Proceedings of the 35th International Conference on Machine Learning Held in Stockholmsm"assan, Stockholm Sweden on 10-15 July 2018 Published as Volume 80 by the Proceedings of Machine Learning Research on 03 July 2018. Volume Edited by: Jennifer Dy Andreas…

4.16K views11:04

Data Science by ODS.ai 🦜

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…

4.74K views15:04

Data Science by ODS.ai 🦜

Toward theoretical understanding of deep learning

http://unsupervised.cs.princeton.edu/deeplearningtutorial.html

#ICML2018 #tutorial #dl

unsupervised.cs.princeton.edu

Toward Theoretical Understanding of Deep Learning: Slides and
Bibliography

Material to accompany ICMLR'18
tutorial.

4.45K views16:39

Data Science by ODS.ai 🦜

Facebook Research at ICML 2018

Seventeen papers by #FAIR at the #ICML2018

https://research.fb.com/facebook-research-at-icml-2018/

4.47K views23:07

Data Science by ODS.ai 🦜

#Nvidia developed approach for cleaning noisy photoes. This comes extremely handy in the radiology.

Link: https://news.developer.nvidia.com/ai-can-now-fix-your-grainy-photos-by-only-looking-at-grainy-photos/?ncid=--45511

#dl #cv

NVIDIA Developer Blog

AI Can Now Fix Your Grainy Photos by Only Looking at Grainy Photos | NVIDIA Developer Blog

What if you could take your photos that were originally taken in low light and automatically remove the noise and artifacts? Have grainy or pixelated images in your photo library and want to fix them?

4.78K viewsedited 08:29

Data Science by ODS.ai 🦜

5.47K views08:29

Data Science by ODS.ai 🦜

ICML 2018 Accepted Papers Stats

Medium post with the meta statistics about accepted papers.

https://medium.com/machine-learning-in-practice/icml-2018-accepted-papers-stats-339f1cad5a55

#ICML2018 #meta #statistics

Medium

ICML 2018 Accepted Papers Stats

The Thirty-fifth International Conference on Machine Learning (ICML) is being held this week in Stockholm Sweden. ICML is one of the most…

6.94K views14:51

Data Science by ODS.ai 🦜

Visitor's highlights on #ICML2018

[ICML 2018] Day 2 - Representation Learning, Networks and Relational Learning

https://gmarti.gitlab.io/ml/2018/07/11/icml18-day-2.html

6.4K views23:40

Data Science by ODS.ai 🦜

Ian Goodfellow (Google Brain) will have a free webinar on Adversarial Machine Learning

https://event.on24.com/eventRegistration/EventLobbyServlet?target=reg20.jsp&partnerref=twitterShareFromReg&ms=1531251848082&eventid=1633807&sessionid=1&key=8B7A8F4B65B54C35752F8A6FE23F641A&regTag=&sourcepage=register

#webinar #google #gbrain

6.22K views13:32

Data Science by ODS.ai 🦜

Very thoroughful notes on #ICML2018

https://david-abel.github.io/blog/posts/misc/icml_2018.pdf

4.86K views21:00

Data Science by ODS.ai 🦜

Learning World Models: The Next Step Towards AI

Video of Yann LeCun's keynote speech. First-hand expectations of closeness of real AI. Spoiler: still not even near yet.

https://www.facebook.com/722677142/posts/10155402036352143/

Facebook

See posts, photos and more on Facebook.

5.63K views21:02