The proceedings of #icml2018 are now online
#paper
https://goo.gl/e5y2Yk @ArtificialIntelligenceArticles
#paper
https://goo.gl/e5y2Yk @ArtificialIntelligenceArticles
Best Paper Awards ICML 2018
Paper: https://arxiv.org/abs/1802.00420
Github: https://github.com/anishathalye/obfuscated-gradients @ArtificialIntelligenceArticles
Paper: https://arxiv.org/abs/1802.00420
Github: https://github.com/anishathalye/obfuscated-gradients @ArtificialIntelligenceArticles
Best Paper Runner Up Awards ICML 2018
Paper: https://www.cse.ust.hk/~huangzf/ICML18.pdf @ArtificialIntelligenceArticles
Paper: https://www.cse.ust.hk/~huangzf/ICML18.pdf @ArtificialIntelligenceArticles
Best Paper Runner Up Awards ICML 2018
Paper: https://arxiv.org/abs/1802.05642 @ArtificialIntelligenceArticles
Paper: https://arxiv.org/abs/1802.05642 @ArtificialIntelligenceArticles
Best Paper Runner Up Awards ICML 2018
Paper: https://arxiv.org/abs/1806.08010 @ArtificialIntelligenceArticles
Paper: https://arxiv.org/abs/1806.08010 @ArtificialIntelligenceArticles
❄️💦10 مقاله برتر یادگیری ماشین به انتخاب Mybridge در ماه گذشته
Machine Learning Top 10 Articles for the Past Month (v.July 2018)
https://goo.gl/St8m63 @ArtificialIntelligenceArticles
Machine Learning Top 10 Articles for the Past Month (v.July 2018)
https://goo.gl/St8m63 @ArtificialIntelligenceArticles
Microsoft Research Open Data
A collection of free datasets from Microsoft Research to advance state-of-the-art research in areas such as natural language processing, computer vision, and domain specific sciences.
https://msropendata.com/
Similar to the AWS version :
https://aws.amazon.com/opendata/
@ArtificialIntelligenceArticles
A collection of free datasets from Microsoft Research to advance state-of-the-art research in areas such as natural language processing, computer vision, and domain specific sciences.
https://msropendata.com/
Similar to the AWS version :
https://aws.amazon.com/opendata/
@ArtificialIntelligenceArticles
Amazon
Open Data on AWS
Sharing data in the cloud lets data users spend more time on data analysis rather than data acquisition. Browse available data and learn how to register your own datasets.
Official Repository for the Deep Reinforcement Learning Nanodegree program
https://github.com/udacity/deep-reinforcement-learning
@ArtificialIntelligenceArticles
https://github.com/udacity/deep-reinforcement-learning
@ArtificialIntelligenceArticles
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
Synthesizing realistic high-resolution images with Glow, a new reversible generative model:
https://blog.openai.com/glow/
@ArtificialIntelligenceArticles
https://blog.openai.com/glow/
@ArtificialIntelligenceArticles
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…
Feature-wise transformations
New review article on feature-wise transformations (like FiLM) in the highly visual and interactive Distill journal. With Vincent Dumoulin, Ethan Perez, Nathan Schucher, Florian Strub, Harm de Vries, Aaron Courville and Yoshua Bengio. Many institutions involved. A very useful building block for learning conditioning computation (especially visual computation).
https://distill.pub/2018/feature-wise-transformations/
@ArtificialIntelligenceArticles
New review article on feature-wise transformations (like FiLM) in the highly visual and interactive Distill journal. With Vincent Dumoulin, Ethan Perez, Nathan Schucher, Florian Strub, Harm de Vries, Aaron Courville and Yoshua Bengio. Many institutions involved. A very useful building block for learning conditioning computation (especially visual computation).
https://distill.pub/2018/feature-wise-transformations/
@ArtificialIntelligenceArticles
Distill
Feature-wise transformations
A simple and surprisingly effective family of conditioning mechanisms.
DeepMind papers at ICML 2018
https://deepmind.com/blog/deepmind-papers-icml-2018/
@ArtificialIntelligenceArticles
https://deepmind.com/blog/deepmind-papers-icml-2018/
@ArtificialIntelligenceArticles
DeepMind
DeepMind papers at ICML 2018 | DeepMind
The 2018 International Conference on Machine Learning will take place in Stockholm, Sweden from 10-15 July. Here you will find a schedule of DeepMind presentations at ICML.
ICML 2018 Tutorial sessions
International Conference on Machine Learning @icmlconf (ICML 2018) a premier annual Machine Learning event is going Live Stream at
ICML 2018 Tutorial sessions (Live Stream )
https://www.facebook.com/icml.imls/videos/428757614305426/
@ArtificialIntelligenceArticles
International Conference on Machine Learning @icmlconf (ICML 2018) a premier annual Machine Learning event is going Live Stream at
ICML 2018 Tutorial sessions (Live Stream )
https://www.facebook.com/icml.imls/videos/428757614305426/
@ArtificialIntelligenceArticles
Facebook
International Conference on Machine Learning
Welcome back to the ICML 2018 Tutorial sessions. This tutorial Optimization Perspectives on Learning to Control will survey the foundations required to build machine learning systems that reliably...
Toward theoretical understanding of deep learning
https://unsupervised.cs.princeton.edu/deeplearningtutorial.html
video :
https://www.facebook.com/icml.imls/videos/428562880991566/
@ArtificialIntelligenceArticles
https://unsupervised.cs.princeton.edu/deeplearningtutorial.html
video :
https://www.facebook.com/icml.imls/videos/428562880991566/
@ArtificialIntelligenceArticles
unsupervised.cs.princeton.edu
Toward Theoretical Understanding of Deep Learning: Slides and
Bibliography
Bibliography
Material to accompany ICMLR'18
tutorial.
tutorial.
Facebook Research at ICML 2018
https://research.fb.com/facebook-research-at-icml-2018/
@ArtificialIntelligenceArticles
https://research.fb.com/facebook-research-at-icml-2018/
@ArtificialIntelligenceArticles
Optimization Perspectives on Learning to Control #ICML2018 #Tutorial
https://people.eecs.berkeley.edu/~brecht/l2c-icml2018/
@ArtificialIntelligenceArticles
https://people.eecs.berkeley.edu/~brecht/l2c-icml2018/
@ArtificialIntelligenceArticles
First human body scan performed.
First 3D colour X-ray of a human using CERN technology https://home.cern/about/updates/2018/07/first-3d-colour-x-ray-human-using-cern-technology
First 3D colour X-ray of a human using CERN technology https://home.cern/about/updates/2018/07/first-3d-colour-x-ray-human-using-cern-technology
Inability of convolutional #neuralnetworks (CNNs) to transform spatial representations between two different types: coordinates in (i, j) Cartesian space and coordinates in one-hot pixel space.
https://eng.uber.com/coordconv/
paper: https://arxiv.org/abs/1807.03247
https://eng.uber.com/coordconv/
paper: https://arxiv.org/abs/1807.03247
Uber Blog
An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution | Uber Blog
As powerful and widespread as convolutional neural networks are in deep learning, AI Labs’ latest research reveals both an underappreciated failing and a simple fix.
AI Can Now Fix Your Grainy Photos by Only Looking at Grainy Photos https://goo.gl/3C6ZpS
paper: https://arxiv.org/abs/1803.04189 @ArtificialIntelligenceArticles
paper: https://arxiv.org/abs/1803.04189 @ArtificialIntelligenceArticles