Google AI announced the release of the Google Research Football Environment, a novel RL environment where agents aim to master the world’s most popular sport—football.

#AIforFootball #GoogleAI

https://ai.googleblog.com/2019/06/introducing-google-research-football.html

Geoffrey Hinton discusses how AI could inform our understanding of the brain
https://venturebeat.com/2019/05/09/geoffrey-hinton-discusses-how-ai-might-inform-our-understanding-of-the-brain/

Announcing PyTorch Hub!

Want ResNet, ResNext, BERT, GPT, PGAN, Tacotron, DenseNet, MobileNet...?
- Pull models with 1 line of code.
- Publish your models by sending a pull request.

More info here: https://pytorch.org/hub

https://pytorch.org/blog/towards-reproducible-research-with-pytorch-hub/

Physical Activity Monitoring Using Smartphone Sensors and Machine Learning
https://towardsdatascience.com/physical-activity-monitoring-using-smartphone-sensors-and-machine-learning-93f51f4e744a

SLIDES
ICML'19 for our Tutorial on Attention in Deep Learning
Alex Smola
Amazon Web Services

https://alex.smola.org/talks/ICML19-attention.pdf

The complete list of all 519 ICML-2019 papers with code. #icml2019 #AI #MachineLearning #ComputerVision #code

https://www.paperdigest.org/2019/05/icml-2019-papers-with-code/

Towards Reproducible Research with PyTorch Hub
Blog by Team PyTorch: https://pytorch.org/blog/towards-reproducible-research-with-pytorch-hub/
#deeplearning #pytorch #research

ICML 2019 videos have been posted https://www.youtube.com/channel/UCvqEpkx-HQ2nDMT-ob-AADg/videos https://t.iss.one/ArtificialIntelligenceArticles

Tutorial: "Meta-Learning: from Few-Shot Learning to Rapid Reinforcement Learning" https://sites.google.com/view/icml19metalearning #ICML2019 https://t.iss.one/ArtificialIntelligenceArticles

Welcome to the ICML 2019 Tutorial session: Active Hypothesis Testing: An Information Theoretic (re)View

Presented by Tara Javidi


https://www.youtube.com/watch?v=tuu56-8BhwM

Welcome to ICML 2019 Tutorial session: Never-Ending Learning

Presented by Tom Mitchell and Partha Talukdar


https://www.youtube.com/watch?v=0TADiY7iPAc

https://t.iss.one/ArtificialIntelligenceArticles

Welcome to the ICML 2019 Tutorial session: A Tutorial on Attention in Deep Learning

Presented by Alex Smola and Aston Zhang

https://www.youtube.com/watch?v=nS1Lse2B48w

New DeepMind Unsupervised Image Model Challenges AlexNet
https://medium.com/syncedreview/new-deepmind-unsupervised-image-model-challenges-alexnet-d658ef92ab1e

ICML 2019 Best Paper Award
https://proceedings.mlr.press/v97/locatello19a.html https://t.iss.one/ArtificialIntelligenceArticles

Rates of Convergence for Sparse Variational Gaussian Process Regression
arxiv.org/abs/1903.03571 https://t.iss.one/ArtificialIntelligenceArticles

CVPR’19 paper on speech-to-gesture prediction. Given raw speech audio, predict arm/hand motion to go along with it. Check out video, or download 128 hours of video for 10 speakers
Learning Individual Styles of Conversational Gesture
https://people.eecs.berkeley.edu/~shiry/speech2gesture/

Congratulations to the Best Papers at the ongoing #ICML2019
The Thirty-sixth International Conference on Machine Learning, Long Beach, USA

(1)Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations https://arxiv.org/pdf/1811.12359.pdf
Congratulations to the GoogleAI team of Francesco Locatello, Stefan Bauer, Mario Lucic, Gunnar Rätsch, Sylvain Gelly,Bernhard Schölkopf, Olivier Bachem

(2)Rates of Convergence for Sparse Variational Gaussian Process Regression
https://arxiv.org/pdf/1903.03571.pdf
Kudos to David R. Burt, Carl E. Rasmussen, Mark van der Wilk of University of Cambridge

ICML is one of the premier machine learning conferences. VideoKen is proud to power deep indexing of the entire ICML 2019 video content. Catch up with all of the exciting tutorials here:

https://search.videoken.com/?orgId=133


#MachineLearning #AI #DeepLearning #AIplayer #ICML2019

Language, trees, and geometry in neural networks
code https://pair-code.github.io/interpretability/bert-tree/
paper https://arxiv.org/pdf/1906.02715.pdf

ICYMI: A project that aims to generate images that depict accurate, vivid, and personalized outcomes of climate change using Cycle-Consistent Adversarial Networks (CycleGANs).

https://www.profillic.com/paper/arxiv:1905.03709