ICLR 2019 MILA, Microsoft, and MIT Share Best Paper Honours https://medium.com/syncedreview/iclr-2019-mila-microsoft-and-mit-share-best-paper-honours-440675d5773e https://t.iss.one/ArtificialIntelligenceArticles

TensorFlow Model Optimization Toolkit — Pruning API

Blog by TensorFlow: https://medium.com/tensorflow/tensorflow-model-optimization-toolkit-pruning-api-42cac9157a6a

#MachineLearning #ModelOptimization #TensorFlow #DeepLearning #NeuralNet

Government of Canada creates Advisory Council on Artificial Intelligence
“Artificial intelligence has enormous potential to help us design the responsive digital services that Canadians demand, but it must be used ethically and responsibly. The Advisory Council on Artificial intelligence will give us essential expertise from across industry, academia and government to make sure we use AI in a way that is transparent, deliberate and accountable.” – The Honourable Joyce Murray, President of the Treasury Board and Minister of Digital Government
From Innovation, Science and Economic Development Canada: https://www.canada.ca/en/innovation-science-economic-development/news/2019/05/government-of-canada-creates-advisory-council-on-artificial-intelligence.html
#artificialintelligence #council #canada

Generative models in Tensorflow 2”

GitHub, by Tim Sainburg: https://github.com/timsainb/tensorflow2-generative-models/

#deeplearning #generativeadversarialnetworks #tensorflow #technology

PyTorch Internals

By Edward Z. Yang: https://web.mit.edu/~ezyang/Public/pytorch-internals.pdf

#deeplearning #artificialintelligence #pytorch

Matrices as Tensor Network Diagrams
By MATH3MA: https://www.math3ma.com/blog/matrices-as-tensor-network-diagrams
#matrix #matrices #tensors #vectors

Another feather added to legendary Prof.Yoshua Bengio !


https://syncedreview.com/2019/05/15/yoshua-bengio-to-lead-new-canadian-advisory-council-on-ai/

Computer Age Statistical Inference - Algorithms, Evidence, & Data Science (FREE book pdf for personal use) - Link Below

Download LINK --> https://web.stanford.edu/~hastie/CASI_files/PDF/casi.pdf

Table of Contents

Part I. Classic Statistical Inference

1. Algorithms & Inference
2. Frequentist Inference
3. Bayesian Inference
4. Fisherian Inference & Maximum Likelihood Estimation
5. Parametric Models & Exponential Families

Part II. Early Computer-Age Methods

6. Empirical Bayes
7. James–Stein Estimation & Ridge Regression
8. Generalized Linear Models & Regression Trees
9. Survival Analysis & the EM Algorithm
10. The Jackknife & the Bootstrap
11. Bootstrap Confidence Intervals
12. Cross-Validation & Estimates of Prediction Error
13. Objective Bayes Inference & MCMC
14. Postwar Statistical Inference & Methodology

Part III. Twenty-First-Century Topics

15. Large-Scale Hypothesis Testing & FDRs
16. Sparse Modeling & the Lasso
17. Random Forests & Boosting
18. Neural Networks & Deep Learning
19. Support-Vector

ICML | 2019
Thirty-sixth International Conference on Machine Learning

#ICML2019 tutorials have been announced.

Schedule here:
https://icml.cc/Conferences/2019/Schedule

#ArtificialIntelligence #DeepLearning #MachineLearning

"A Few Unusual Autoencoders"

By Colin Raffel: https://colinraffel.com/talks/vector2018few.pdf

#ArtificialIntelligence #DeepLearning #MachineLearning #NeuralNetworks #VariationalAutoencoder

A PhD graduate Lucy A. Taylor shares the advice she and her colleagues wish they had received before starting their PhD.

https://www.nature.com/articles/d41586-018-07332-x

One of the thorniest debates in neuroscience is whether people can make new neurons after their brains stop developing in adolescence—a process known as neurogenesis.

Now, a new study finds that even people long past middle age can make fresh brain cells, and that past studies that failed to spot these newcomers may have used flawed methods.



https://www.sciencemag.org/news/2019/03/new-neurons-life-old-people-can-still-make-fresh-brain-cells-study-finds

[New Research] Ian Goodfellow and other Google researchers on semi-supervised learning
https://medium.com/ai%C2%B3-theory-practice-business/ai-scholar-a-holistic-approach-to-semi-supervised-learning-51d82a2ee759

Now, this is something outstanding!😀
Paper-Title: Learning 3D Human Dynamics from Video
#UCB #CVPR_2019
Link to the paper: https://arxiv.org/pdf/1812.01601.pdf
Link to the Github: https://github.com/akanazawa/human_dynamics
Link to the Project page: https://akanazawa.github.io/human_dynamics/

TL;DR: They propose an end-to-end model that learns a model of 3D human dynamics that can 1) obtain smooth 3D prediction from video and 2) hallucinate 3D dynamics on single images at test time.

Here is a list of accepted papers and scheduled presentations.

https://docs.google.com/spreadsheets/u/1/d/1RU2y-iuzwtAR_hn4V9yz1qpZSiElm3iaCpUoDJ-vfvQ/htmlview?sle=true#

Foundations of Machine Learning - A Great Book on Machine Learning

By Mehryar Mohri, Afshin Rostamizadeh, and Ameet Talwalkar

MIT Press, Second Edition, 2018

Dr Mehryar Mohri is a Professor of Computer Science and Mathematics at Courant Institute of Mathematical Sciences, New York University

"This book is a general introduction to machine learning that can serve as a textbook for graduate students and a reference for researchers. It covers fundamental modern topics in machine learning while providing the theoretical basis and conceptual tools needed for the discussion and justification of algorithms. It also describes several key aspects of the application of these algorithms. The authors aim to present novel theoretical tools and concepts while giving concise proofs even for relatively advanced topics. Foundations of Machine Learning is unique in its focus on the analysis and theory of algorithms."

Online Edition:

https://mitpress.ublish.com/ereader/7093/?preview#page/Cover

Deep learning and the Schrödinger equation

By Mills et al.: https://arxiv.org/abs/1702.01361

#ArtificialInteligence #Science #DeepLearning #MachineLearning #Physics #MontrealAI

Translatotron is the first end-to-end model that can directly translate speech from one language into speech in another language. It is also able to retain the source speaker’s voice in the translated speech.


https://ai.googleblog.com/2019/05/introducing-translatotron-end-to-end.html

Meta-Learning with Differentiable Convex Optimization #CVPR2019 Oral

Few-shot learning SoTA on miniImageNet, tieredImageNet, CIFAR-FS, and FC100

Github
https://github.com/kjunelee/MetaOptNet

ArXiv

https://arxiv.org/abs/1904.03758

Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning

Garcez et al.: https://arxiv.org/abs/1905.06088

#ArtificialIntelligence #DeepLearning #MachineLearning