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…
Google AI - Release of Handbook Tutorials on Learning Keras and OpenCV
Hi everyone. I'm happy to let people know that we (Developer Relations at Google AI) are releasing handbooks and accompany presentations/code labs for learning Keras/OpenCV. The material is written for software engineers whom want a 'straight path with no math' to learning machine learning. The handbooks and code samples are free to download (licensed under CC-BY and Apache 2.0).
https://github.com/GoogleCloudPlatform/keras-idiomatic-programmer
Hi everyone. I'm happy to let people know that we (Developer Relations at Google AI) are releasing handbooks and accompany presentations/code labs for learning Keras/OpenCV. The material is written for software engineers whom want a 'straight path with no math' to learning machine learning. The handbooks and code samples are free to download (licensed under CC-BY and Apache 2.0).
https://github.com/GoogleCloudPlatform/keras-idiomatic-programmer
GitHub
GitHub - GoogleCloudPlatform/keras-idiomatic-programmer: Books, Presentations, Workshops, Notebook Labs, and Model Zoo for Software…
Books, Presentations, Workshops, Notebook Labs, and Model Zoo for Software Engineers and Data Scientists wanting to learn the TF.Keras Machine Learning framework - GitHub - GoogleCloudPlatform/ker...
This is a PyTorch implementation of "MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing" (ICML 2019) that I made. MixHop has a state-of-the-art performance on several node classification benchmarks. In addition, the approximate version is pretty scalable. Enjoy!
https://github.com/benedekrozemberczki/MixHop-and-N-GCN
https://github.com/benedekrozemberczki/MixHop-and-N-GCN
GitHub
GitHub - benedekrozemberczki/MixHop-and-N-GCN: An implementation of "MixHop: Higher-Order Graph Convolutional Architectures via…
An implementation of "MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing" (ICML 2019). - benedekrozemberczki/MixHop-and-N-GCN
Nice new work from FAIR on assessing bias in datasets.
Turns out image recognition systems will recognize everyday objects more reliably if the picture was shot in developed countries than if it was shot in the developing world.
A critique of early approaches to visual object recognition was that they could not take context into account to help with the recognition. Now they do.....a bit too much.
https://ai.facebook.com/blog/new-way-to-assess-ai-bias-in-object-recognition-systems/
Turns out image recognition systems will recognize everyday objects more reliably if the picture was shot in developed countries than if it was shot in the developing world.
A critique of early approaches to visual object recognition was that they could not take context into account to help with the recognition. Now they do.....a bit too much.
https://ai.facebook.com/blog/new-way-to-assess-ai-bias-in-object-recognition-systems/
Facebook
A new way to assess AI bias in object-recognition systems
Facebook AI researchers have published the first systematic study that measures the accuracy of object-recognition systems for different communities across the world.