Provably efficient reinforcement learning with rich observations.
https://www.microsoft.com/en-us/research/blog/provably-efficient-reinforcement-learning-with-rich-observations/
https://www.microsoft.com/en-us/research/blog/provably-efficient-reinforcement-learning-with-rich-observations/
Microsoft Research
Provably efficient reinforcement learning is very satisfying indeed.
Despite remarkable achievements, applying reinforcement learning to real-world scenarios remains a challenge. Discover how Microsoft researchers achieve provable efficiency in reinforcement learning with the help of a new algorithm.
This is probably the best #PyTorch Deep Learning course I have encountered.
https://fleuret.org/dlc/
https://fleuret.org/dlc/
fleuret.org
UNIGE 14x050 – Deep Learning
Slides and virtual machine for François Fleuret's Deep Learning Course
andrew ng : ML+ radiologist outperforms a human radiologist alone at detecting cerebral aneurysms.
Deep Learning–Assisted Diagnosis of Cerebral Aneurysms https://news.stanford.edu/2019/06/07/ai-tool-helps-radiologists-detect-brain-aneurysms/
Deep Learning–Assisted Diagnosis of Cerebral Aneurysms https://news.stanford.edu/2019/06/07/ai-tool-helps-radiologists-detect-brain-aneurysms/
Visualizing and Measuring the Geometry of BERT
Coenen, Reif, Yuan et al.: https://arxiv.org/pdf/1906.02715.pdf
#ArtificialIntelligence #DeepLearning #BERT #NLP
Coenen, Reif, Yuan et al.: https://arxiv.org/pdf/1906.02715.pdf
#ArtificialIntelligence #DeepLearning #BERT #NLP
Language, trees, and geometry in neural networks
code https://pair-code.github.io/interpretability/bert-tree/
paper https://arxiv.org/pdf/1906.02715.pdf
code https://pair-code.github.io/interpretability/bert-tree/
paper https://arxiv.org/pdf/1906.02715.pdf
Population-based Augmentation
1000x Faster Data Augmentation
Daniel Ho, Eric Liang, Richard Liaw Jun 7, 2019
https://bair.berkeley.edu/blog/2019/06/07/data_aug/
paper https://arxiv.org/pdf/1905.05393.pdf
1000x Faster Data Augmentation
Daniel Ho, Eric Liang, Richard Liaw Jun 7, 2019
https://bair.berkeley.edu/blog/2019/06/07/data_aug/
paper https://arxiv.org/pdf/1905.05393.pdf
Material used for Deep Learning related workshops for Machine Learning Tokyo
Implementation and Cheat Sheet: https://github.com/Machine-Learning-Tokyo/DL-workshop-series
#artificialintelligence #deeplearning #machinelearning
Implementation and Cheat Sheet: https://github.com/Machine-Learning-Tokyo/DL-workshop-series
#artificialintelligence #deeplearning #machinelearning
Residual Flows for Invertible Generative Modeling
Chen et al.: https://arxiv.org/abs/1906.02735
#artificialintelligence #deeplearning #generativemodels
Chen et al.: https://arxiv.org/abs/1906.02735
#artificialintelligence #deeplearning #generativemodels
Hot Papers from Google Brain, DeepMind and Facebook AI
https://www.google.com/amp/s/syncedreview.com/2019/06/02/hot-papers-from-google-brain-deepmind-and-facebook-ai/amp/
https://www.google.com/amp/s/syncedreview.com/2019/06/02/hot-papers-from-google-brain-deepmind-and-facebook-ai/amp/
Synced
‘Hot’ Papers from Google Brain, DeepMind and Facebook AI
Synced Global AI Weekly June 2nd
A machine-learning model from MIT researchers computationally breaks down how segments of amino acid chains determine a protein’s function, which could help researchers design and test new proteins for drug development or biological research.
https://news.mit.edu/2019/machine-learning-amino-acids-protein-function-0322
https://news.mit.edu/2019/machine-learning-amino-acids-protein-function-0322
MIT News | Massachusetts Institute of Technology
Model learns how individual amino acids determine protein function
A model from MIT researchers “learns” vector embeddings of each amino acid position in a 3-D protein structure, which can be used as input features for machine-learning models to predict amino acid segment functions for drug development and biological research.
Yann LeCun et al. publishing evolutionary algorithm tools. Welcoming the era of deep neuroevolution indeed! (https://eng.uber.com/deep-neuroevolution) Great to see the traditional ML community adopt these tools in the cases when they are useful.
Disentangling Disentanglement in Variational Autoencoders
Mathieu et al.: https://proceedings.mlr.press/v97/mathieu19a.html
#ArtificialIntelligence #DeepLearning #VariationalAutoencoders #VAE
Mathieu et al.: https://proceedings.mlr.press/v97/mathieu19a.html
#ArtificialIntelligence #DeepLearning #VariationalAutoencoders #VAE
PMLR
Disentangling Disentanglement in Variational Autoencoders
We develop a generalisation of disentanglement in variational autoencoders (VAEs)—decomposition of the latent representation—characterising it as the fulfilm...
Best of arXiv.org for AI, Machine Learning, and Deep Learning – April 2019 by insidebigdata
https://insidebigdata.com/2019/05/22/best-of-arxiv-org-for-ai-machine-learning-and-deep-learning-april-2019/
https://insidebigdata.com/2019/05/22/best-of-arxiv-org-for-ai-machine-learning-and-deep-learning-april-2019/
insideBIGDATA
Best of arXiv.org for AI, Machine Learning, and Deep Learning – April 2019
In this recurring monthly feature, we will filter all the recent research papers appearing in the arXiv.org preprint server for subjects relating to AI, [...]
#IntelAI Research has 6 paper acceptances at #ICML2019! Find full list of papers and more here: https://www.intel.ai/icml-2019/
All 1,294 papers at #CVPR2019
Index: https://openaccess.thecvf.com/content_CVPR_2019/html/
#ArtificialIntelligence #DeepLearning #MachineLearning
Index: https://openaccess.thecvf.com/content_CVPR_2019/html/
#ArtificialIntelligence #DeepLearning #MachineLearning
Practical Deep Learning with Bayesian Principles
Osawa et al.: https://arxiv.org/pdf/1906.02506.pdf
#Bayesian #DeepLearning #PyTorch #VariationalInference
Osawa et al.: https://arxiv.org/pdf/1906.02506.pdf
#Bayesian #DeepLearning #PyTorch #VariationalInference
Butterfly Transform: An Efficient FFT Based Neural Architecture Design
Alizadeh et al.: https://arxiv.org/abs/1906.02256
#ArtificialIntelligence #DeepLearning #MachineLearning
Alizadeh et al.: https://arxiv.org/abs/1906.02256
#ArtificialIntelligence #DeepLearning #MachineLearning
arXiv.org
Butterfly Transform: An Efficient FFT Based Neural Architecture Design
In this paper, we show that extending the butterfly operations from the FFT algorithm to a general Butterfly Transform (BFT) can be beneficial in building an efficient block structure for CNN...
Computational Narrative Intelligence and the Quest for the Great Automatic Grammatizator
Slides by Mark Riedl: https://www.dropbox.com/s/2o8enj7amaxxx1y/naacl-nu-ws.pdf?dl=0
#ArtificialIntelligence #MachineLearning #NaturalLanguageProcessing
Slides by Mark Riedl: https://www.dropbox.com/s/2o8enj7amaxxx1y/naacl-nu-ws.pdf?dl=0
#ArtificialIntelligence #MachineLearning #NaturalLanguageProcessing
very interesting hypothesis by Yoshua Bengio https://arxiv.org/abs/1901.10912
MicrosoftAI raises the bar in text-to-speech with an “almost” unsupervised context, training ONLY 200 speech and text data to generate human-sounding speech for about 20mins - 99.84% world level intelligible rate.
Paper: https://arxiv.org/pdf/1905.06791.pdf
Sample: buff.ly/2X885F9
Paper: https://arxiv.org/pdf/1905.06791.pdf
Sample: buff.ly/2X885F9