Russia's sudden change of heart on AI


https://www.msn.com/en-xl/europe/top-stories/russias-sudden-change-of-heart-on-ai/ar-AAAXoYs

Approximate Bayesian Inference Using SGD Trajectory

code https://github.com/wjmaddox/swa_gaussian

video SWAG: Approximate Bayesian Inference Using SGD Trajectory

paper https://arxiv.org/pdf/1902.02476.pdf

Interesting article to read about handling unlabeled data
https://arxiv.org/abs/1905.00546

Let join to learn and get rewards with your ideas

https://www.microsoft.com/en-us/ai/ai-idea-challenge

Exponential Family Estimation via Adversarial Dynamics Embedding

Dai et al.: https://arxiv.org/abs/1904.12083

#ArtificialIntelligence #DeepLearning #MachineLearning

OpenAI Gym : Make a two-dimensional bipedal robot walk forward as fast as
possible!!! https://gym.openai.com/evaluations/eval_pt663BoRS9mTUCCdGcsf4A
#AI #DeepLearning #ReinforcementLearning

Yining Shi just made three Doodle Classifier experiments with Tensorflow.js:
1. Train a doodle classifier with tf.js
2. Train a doodle classifier with 345 classes
3. KNN doodle classifier
Code and demo: https://github.com/yining1023/doodleNet
#MachineLearning #TensorFlow #tensorflowjs #doodles

Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning

Wortsman et al.: https://arxiv.org/abs/1812.00971

#ArtificialIntelligence #DeepLearning #MetaLearning

This is last lecture in the series on Wasserstein GAN. In this lecture implementation of Wasserstein Generative Adversarial Network (WGAN) is performed in TensorFlow using Google Colab.
https://youtu.be/XK0TJPeZVbs
You can subscribe channel for more such videos
https://www.youtube.com/user/kumarahlad/featured?sub_confirmation=1

Live : iclr conference 2019

https://www.facebook.com/iclr.cc/videos/2261061694154984/

@ArtificialIntelligenceArticles

"Wasserstein GAN"

Written by James Allingham: https://www.depthfirstlearning.com/2019/WassersteinGAN

#DeepLearning #GenerativeModels #GenerativeAdversarialNetworks

The Biological Roots of Intelligence
Imaging, behavioral, and genetic data yield clues to what’s behind effective thinking.
https://www.the-scientist.com/features/the-biological-roots-of-intelligence-64931

This new scholarship program, announced at [F8](https://www.f8.com/), the Facebook Developer Conference in San Jose, will enable students to acquire skills in Federated Learning, Differential Privacy, and Encrypted Computation with the benefit of robust community support from Udacity. You will learn how to use the newest privacy-preserving technologies, such as [OpenMined’s](https://openmined.org/) PySyft. [PySyft](https://github.com/OpenMined/PySyft) extends [PyTorch](https://pytorch.org/) and other deep learning tools with the cryptographic and distributed technologies necessary to safely and securely train AI models on distributed private data while maintaining users’ privacy. Students will also have the opportunity to earn their way to a full scholarship to either the[ Deep Learning Nanodegree program](https://www.udacity.com/course/deep-learning-nanodegree--nd101) or the [Computer Vision Nanodegree program](https://www.udacity.com/course/computer-vision-nanodegree--nd891) with Udacity.

#FacebookAI #Udacity #AIScholarship #PrivateAI

Free datasets of russian speech
https://habr.com/ru/post/450760/

Best paper Award ICLR 2019


https://iclr.cc/Conferences/2019/Awards

What's the verdict on Tensorflow Federated (TFF)? Anyone have a chance to use this on distributed data sets yet?
https://medium.com/tensorflow/introducing-tensorflow-federated-a4147aa20041

Universal Transformers

Blog by Mostafa Dehghani : https://mostafadehghani.com/2019/05/05/universal-transformers/

#artificialintelligence #deeplearning #technology

"Deep Generative Models for Graphs: Methods & Applications"

Slides by Jure Leskovec :
https://i.stanford.edu/~jure/pub/talks2/graph_gen-iclr-may19-long.pdf

#artificialintelligence #deeplearning #machinelearning #ICLR2019