See comment on new Chinese AI ethics principles: https://www.technologyreview.com/s/613610/why-does-china-suddenly-care-about-ai-ethics-and-privacy/
MIT Technology Review
Why does Beijing suddenly care about AI ethics?
New guidelines on freedom and privacy protection signal that the Chinese state is open to dialogue about how it uses technology.
This new paper shows how to use #machinelearning to steal pins and passwords using only the sound you make when typing them on your phone or tablet.
Download Link: https://arxiv.org/pdf/1903.11137.pdf
Download Link: https://arxiv.org/pdf/1903.11137.pdf
Deep Learning Gallery - a curated list of awesome deep learning projects
https://deeplearninggallery.com/
https://deeplearninggallery.com/
Deeplearninggallery
Deep Learning Gallery - a curated list of awesome deep learning projects
Showcase of the best deep learning algorithms and deep learning applications.
Deep Learning with MATLAB: Deep Learning in 11 Lines of MATLAB Code
https://nl.mathworks.com/videos/deep-learning-in-11-lines-of-matlab-code-1481229977318.html
https://nl.mathworks.com/videos/deep-learning-in-11-lines-of-matlab-code-1481229977318.html
Mathworks
Deep Learning: Deep Learning in 11 Lines of MATLAB Code
See how to use MATLAB, a simple webcam, and a deep neural network to identify objects in your surroundings. This demo uses AlexNet, a pretrained deep convolutional neural network that has been trained on over a million images.
Energy and Policy Considerations for Deep Learning in NLP.
https://drive.google.com/file/d/1v3TxkqPuzvRfiV_RVyRTTFbHl1pZq7Ab/view
https://drive.google.com/file/d/1v3TxkqPuzvRfiV_RVyRTTFbHl1pZq7Ab/view
Google Docs
acl2019.pdf
Quantum entanglement begat space-time.
Fascinating.
Those AdS spaces look a lot like Maximilian Nickel's hyperbolic space embeddings.
And those MERA tensor networks look a lot like ConvNets.
https://www.nature.com/news/the-quantum-source-of-space-time-1.18797
Fascinating.
Those AdS spaces look a lot like Maximilian Nickel's hyperbolic space embeddings.
And those MERA tensor networks look a lot like ConvNets.
https://www.nature.com/news/the-quantum-source-of-space-time-1.18797
Nature News & Comment
The quantum source of space-time
Many physicists believe that entanglement is the essence of quantum weirdness — and some now suspect that it may also be the essence of space-time geometry.
New slides: "Pretraining for Generation" at neuralgen 2019 Includes
overview of methods and new gpt-2 experiments on "pseudo-self attention"
Alexander Rush(Zack Ziegler, Luke Melas-Kyriazi, Sebastian Gehrmann)HarvardNLP / Cornell Tech
https://nlp.seas.harvard.edu/slides/Pre-training%20for%20Generation.pdf
overview of methods and new gpt-2 experiments on "pseudo-self attention"
Alexander Rush(Zack Ziegler, Luke Melas-Kyriazi, Sebastian Gehrmann)HarvardNLP / Cornell Tech
https://nlp.seas.harvard.edu/slides/Pre-training%20for%20Generation.pdf
Reliability in Reinforcement Learning
https://www.microsoft.com/en-us/research/blog/reliability-in-reinforcement-learning/?ocid=msr_blog_reliabrl_tw
https://www.microsoft.com/en-us/research/blog/reliability-in-reinforcement-learning/?ocid=msr_blog_reliabrl_tw
Encrypted Deep Learning Classification with PyTorch &
PySyft
https://blog.openmined.org/encrypted-deep-learning-classification-with-pysyft/
PySyft
https://blog.openmined.org/encrypted-deep-learning-classification-with-pysyft/
Driver Behavior Analysis Using Lane Departure Detection Under Challenging Conditions. arxiv.org/abs/1906.00093
Mesh R-CNN
Gkioxari et al.: https://arxiv.org/abs/1906.02739
#ArtificialIntelligence #DeepLearning #MachineLearning
Gkioxari et al.: https://arxiv.org/abs/1906.02739
#ArtificialIntelligence #DeepLearning #MachineLearning
arXiv.org
Mesh R-CNN
Rapid advances in 2D perception have led to systems that accurately detect objects in real-world images. However, these systems make predictions in 2D, ignoring the 3D structure of the world....
Robustness beyond Security: Computer Vision Applications
Engstrom et al.: https://gradientscience.org/robust_apps/
#artificialintelligence #computervision #security #technology
Engstrom et al.: https://gradientscience.org/robust_apps/
#artificialintelligence #computervision #security #technology
gradient science
Robustness Beyond Security: Computer Vision Applications
An off-the-shelf robust classifier can be used to perform a range of computer vision tasks beyond classification.
SuperGLUE
A new benchmark styled after GLUE with a new set of more difficult language understanding tasks, improved resources, and a new public leaderboard: https://super.gluebenchmark.com
#ArtificialIntelligence #DeepLearning #MachineLearning
A new benchmark styled after GLUE with a new set of more difficult language understanding tasks, improved resources, and a new public leaderboard: https://super.gluebenchmark.com
#ArtificialIntelligence #DeepLearning #MachineLearning
SuperGLUE Benchmark
SuperGLUE is a new benchmark styled after original GLUE benchmark with a set of more difficult language understanding tasks, improved resources, and a new public leaderboard.
What parts of ML can be designed?" Check out the colab made to introduce ML concepts
Michelle R Carney
https://colab.research.google.com/drive/16ih9JPh1FQi6_XETj2e4G4JYYI5Qe0BI#scrollTo=X8FyAQo-t2uF
Michelle R Carney
https://colab.research.google.com/drive/16ih9JPh1FQi6_XETj2e4G4JYYI5Qe0BI#scrollTo=X8FyAQo-t2uF
Google
Google Colaboratory
#Deeplearning #Automation #Scheduling
A recent success of AI & Deep learning for multi-machine/robot scheduling problems!
Arxiv link https://arxiv.org/abs/1905.12204
Three issues are particularly important in this context: quality of the resulting decisions, scalability, and transferability.
Please check out the recent research which addressed those challenges! 96% optimality, transferable only with 1% loss in performance.
A recent success of AI & Deep learning for multi-machine/robot scheduling problems!
Arxiv link https://arxiv.org/abs/1905.12204
Three issues are particularly important in this context: quality of the resulting decisions, scalability, and transferability.
Please check out the recent research which addressed those challenges! 96% optimality, transferable only with 1% loss in performance.
XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks by Mohammad Rastegari
https://videolectures.net/eccv2016_rastegari_neural_networks/?q=eccv%202016
https://videolectures.net/eccv2016_rastegari_neural_networks/?q=eccv%202016
videolectures.net
XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
We propose two efficient approximations to standard convolutional neural networks: Binary-Weight-Networks and XNOR-Networks. In Binary-Weight-Networks, the filters are approximated with binary values resulting in 32x memory saving. In XNOR-Networks, both…