IBM researchers use analog memory to train deep NeuralNetworks faster than with GPUs, using hundreds of times less energy: http://goo.gl/jB4BWW paper : http://goo.gl/u1EE6C

NCRF++: An Open-source Neural Sequence Labeling Toolkit
GitHub : https://github.com/jiesutd/NCRFpp
paper : https://arxiv.org/abs/1806.05626 @ArtificialIntelligenceArticles

End-to-End Parkinson Disease Diagnosis using Brain MR-Images by 3D-CNN. http://arxiv.org/abs/1806.05233 @ArtificialIntelligenceArticles

Deep Video Portraits

Photo-realistic reanimation of portrait videos. Transfer full 3D head pose, facial expression, eye gaze and blinking.

ArXiv
https://arxiv.org/abs/1805.11714
Full Demo
https://www.youtube.com/watch?v=qc5P2bvfl44

https://yangx.top/ArtificialIntelligenceArticles

Deep Generative Models in the Real-World: An Open Challenge from Medical Imaging. http://arxiv.org/abs/1806.05452 @ArtificialIntelligenceArticles

Face detection and face recognition in the browser with tensorflow.js

https://github.com/justadudewhohacks/face-api.js/tree/face-landmarks

https://yangx.top/ArtificialIntelligenceArticles

Nvidia researchers use deep learning to create super-slow motion videos
The researchers used Nvidia Tesla V100 GPUs and cuDNN-accelerated PyTorch deep learning framework to train their system on more than 11,000 videos shot at 240 frames-per-se

Transforming Standard Video Into Slow Motion with Machine Learning

https://news.developer.nvidia.com/transforming-standard-video-into-slow-motion-with-ai/

paper : https://arxiv.org/abs/1712.00080

https://yangx.top/ArtificialIntelligenceArticles

Here is the June 19 issue of Computer Vision News

مصاحبه‌ی روزنامه‌ی CVPR2018 با خانم نسرین مصطفی‌زاده http://goo.gl/46kGnH @ArtificialIntelligenceArticles

CVPR 2018 best paper
بهترین مقاله در کنفرانس CVPR 2018
http://taskonomy.stanford.edu/ or
https://arxiv.org/abs/1804.08328 @ArtificialIntelligenceArticles

Best student paper award cvpr 2018 https://arxiv.org/abs/1801.01615 @ArtificialIntelligenceArticles

Researchers from NVIDIA just received the #CVPR2018 “Best Paper Honorable Mention Award,” for their paper, “SPLATNet: Sparse Lattice Networks for Point Cloud Processing."

paper : https://arxiv.org/abs/1802.08275

https://news.developer.nvidia.com/nvidia-splatnet-research-paper-wins-a-major-cvpr-2018-award/

https://yangx.top/ArtificialIntelligenceArticles

CVPR 2018 Best Paper: Geometric #DeepLearning - CodeSLAM - Learning a Compact, Optimisable Representation for Dense Visual SLAM
paper: https://arxiv.org/abs/1804.00874 @ArtificialIntelligenceArticles

Machine Learning Papers with Code - A searchable site that links machine learning papers on ArXiv with code on GitHub
https://paperswithcode.com/ @ArtificialIntelligenceArticles

Andrew Ng, Stanford - Stanford Medicine Big Data | Precision Health 2018 video : https://bit.ly/2tmW1D5 @ArtificialIntelligenceArticles

Machine Learning Open Source Projects of the Month (v.June 2018)
http://goo.gl/3wavFQ @ArtificialIntelligenceArticles

awesome project: turning youtube videos of soccer games into augmented reality scenes on a tabletop http://goo.gl/18ybiH @ArtificialIntelligenceArticles

OpenAI Five !

A team of five neural networks, OpenAI Five, has started to defeat amateur human teams (including a semi-pro team) at Dota 2 http://goo.gl/CjEq68 @ArtificialIntelligenceArticles

Super fun dataset and challenge : Fashion-Gen: The Generative Fashion Dataset and Challenge

More details about the Fashion-Gen dataset (Text to Image generation) and the challenge:

https://arxiv.org/abs/1806.08317

Participate in the challenge http://fashion-gen.com/ to win 2000$ and submit your paper to

https://sites.google.com/view/eccvfashion/

https://yangx.top/ArtificialIntelligenceArticles

NIPS 2018: AI for Prosthetics Challenge

Reinforcement learning with musculoskeletal models

Objective : to bring deep reinforcement learning to solve problems in medicine

https://www.crowdai.org/challenges/nips-2018-ai-for-prosthetics-challenge

https://yangx.top/ArtificialIntelligenceArticles

Meet the Godfather of AI(Geoffrey Hinton )

"It was just obvious to me that it was the right way to go. The brain's a big neural network. And so, it has to be that stuff like this can work, because it works in our brains. There's just never any doubt about that." - Geoffrey Hinton


A new interview with Geoffrey Hinton

video :

https://www.youtube.com/watch?v=l9RWTMNnvi4&feature=youtu.be

https://yangx.top/ArtificialIntelligenceArticles

Turning Fortnite into PUBG with Deep Learning (CycleGAN)
https://towardsdatascience.com/turning-fortnite-into-pubg-with-deep-learning-cyclegan-2f9d339dcdb0 @ArtificialIntelligenceArticles