Probabilistic Meta-Representations Of Neural Networks

Karaletsos et al. : https://www.gatsby.ucl.ac.uk/~balaji/udl-camera-ready/UDL-13.pdf

SOTAWHAT - A script to keep track of state-of-the-art AI research

Post: https://huyenchip.com/2018/10/04/sotawhat.html
GitHub: https://github.com/chiphuyen/sotawhat

Why we need to continue to try to better understand human/animal brains for #AI research. "Neuroscience-Inspired Artificial Intelligence" https://www.cell.com/neuron/fulltext/S0896-6273(17)30509-3

Connections between physics and deep learning
https://www.youtube.com/watch?v=5MdSE-N0bxs @ArtificialIntelligenceArticles

Human Pose Estimation 101

By Sudharshan Chandra Babu: https://github.com/cbsudux/Human-Pose-Estimation-101

CosmoFlow: Using Deep Learning to Learn the Universe at Scale
arxiv.org/abs/1808.04728 #deeplearning #physics #universe

Imperial College Mathematics department Deep Learning course

From scratch to BigGANs : https://www.deeplearningmathematics.com

#artificialintelligence #deeplearning #mathematics

Google DeepMind founder Demis Hassabis: Three truths about AI

1) AI will save us from ourselves
2) AI will lead to Nobel-prize winning science breakthroughs
3) Deep learning is not enough to crack AI


video : https://www.techrepublic.com/videos/artificial-intelligence-is-vital-for-business-but-its-no-magic-bullet/


https://www.techrepublic.com/google-amp/article/google-deepmind-founder-demis-hassabis-three-truths-about-ai/

https://t.iss.one/ArtificialIntelligenceArticles

Announcing fast.ai part 1 now available as Kaggle Kernels

Blog by William Horton : https://medium.com/@hortonhearsafoo/announcing-fast-ai-part-1-now-available-as-kaggle-kernels-8ef4ca3b9ce6

Where Did My Optimum Go? : An Empirical Analysis of Gradient Descent Optimization in Policy Gradient Methods

Henderson et al.: https://arxiv.org/abs/1810.02525

ArviZ: Exploratory analysis of Bayesian models

Includes functions for posterior analysis, model checking, comparison and diagnostics.

GitHub : https://github.com/arviz-devs/arviz

Video lectures of MLSS2018, Tubingen.

You can learn various ML topics from big names, e.g., Scholkopf, Jordan, Ghahramani, Salakhutdinov, Mnih, Peters, Schaal, etc. https://goo.gl/1ahzJh

Talos : Hyperparameter Scanning and Optimization for Keras

Code : https://github.com/autonomio/talos

#ai #bigdata #machinelearning

PHYSICS | MACHINE LEARNING

Recent papers combining the fields of physics - especially quantum mechanics - and machine learning : https://physicsml.github.io/pages/papers.html

This is a great interview with the very smart AndrewYNg, talking baout the future of #AI https://fortune.com/2018/10/06/andrew-ng-artificial-intelligence-authority/

Did the Model Understand the Question?

https://arxiv.org/pdf/1805.05492.pdf

Code and SLIDES

Adversarial Attacks on Question Answering models


https://github.com/pramodkaushik/acl18_results


https://github.com/pramodkaushik/acl18_results/blob/master/talk_slides_ACL2018.pdf

https://t.iss.one/ArtificialIntelligenceArticles

Learning New Physics from a Machine.

https://arxiv.org/abs/1806.02350

#deeplearning #machinelearning #physics

Machine Learning for New Physics Searches https://arxiv.org/abs/1809.11150 @ArtificialIntelligenceArticles

Career advice for recent Computer Science graduates

By Chip Huyen : https://huyenchip.com/2018/10/08/career-advice-recent-cs-graduates.html @ArtificialIntelligenceArticles

Machine Learning Top 10 Articles for the Past Month (v.Oct 2018)

https://goo.gl/KrXmVg @ArtificialIntelligenceArticles