fast.ai

Making neural nets uncool again

Learn :

- Intro Machine Learning : https://course.fast.ai/ml

- Practical Deep Learning : https://course.fast.ai/

- Cutting Edge Deep Learning : https://course.fast.ai/part2.html

- Computational Linear Algebra : https://github.com/fastai/numerical-linear-algebra

@ArtificialIntelligenceArticles

Industrial AI: BHGE’s Physics-based, Probabilistic Deep Learning Using TensorFlow Probability - Part 1
https://goo.gl/Sbkwru @ArtificialIntelligenceArticles

Here are 660 free online programming and computer science courses you can start in October https://medium.freecodecamp.org/99725c056812

Self-Attention GAN

Tensorflow implementation for reproducing main results in the paper "Self-Attention Generative Adversarial Networks" : https://github.com/brain-research/self-attention-gan

Paper : https://arxiv.org/abs/1805.08318

#artificialintelligence #deeplearning #neuralnetworks

Deep Recurrent Level Set for Segmenting Brain Tumors. https://arxiv.org/abs/1810.04752

Quantum Deep Learning
https://arxiv.org/abs/1412.3489

Next Fall, the Institute for Pure and Applied Mathematics at UCLA (IPAM) will host a semester-long program entitled "Machine Learning for Physics and the Physics of Learning".

Among other events, there will be four one-week-long workshops:
- Workshop I: From Passive to Active: Generative and Reinforcement Learning with Physics (September 23 - 27, 2019) co-organized by Alan Aspuru-Guzik.


https://www.ipam.ucla.edu/programs/workshops/workshop-i-from-passive-to-active-generative-and-reinforcement-learning-with-physics/

- Workshop II: Interpretable Learning in Physical Sciences (October 14 - 18, 2019) co-organized by my NYU colleague Kyle Cranmer. https://www.ipam.ucla.edu/programs/workshops/workshop-ii-interpretable-learning-in-physical-sciences/

- Workshop III: Validation and Guarantees in Learning Physical Models: from Patterns to Governing Equations to Laws of Nature (October 28 - November 1, 2019) co-organized by my NYU colleague Joan Bruna Estrach
https://www.ipam.ucla.edu/programs/workshops/workshop-iii-validation-and-guarantees-in-learning-physical-models-from-patterns-to-governing-equations-to-laws-of-nature/

- Workshop IV: Using Physical Insights for Machine Learning (November 18 - 22, 2019) which I co-organize with Riccardo Zecchina, Lenka Zdeborova and Matthias Rupp. https://www.ipam.ucla.edu/programs/workshops/workshop-iv-using-physical-insights-for-machine-learning/

Tons of fascinating topics in perspective with new applications of ML/DL.

https://www.ipam.ucla.edu/programs/long-programs/machine-learning-for-physics-and-the-physics-of-learning/

@ArtificialIntelligenceArticles

Review Article: Deep Learning in Neuroradiology https://www.ajnr.org/content/39/10/1776 @ArtificialIntelligenceArticles

MedicalTorch is an open-source framework for pytorch, implemeting an extensive set of loaders, pre-processors and datasets for medical imaging.
https://medicaltorch.readthedocs.io/en/stable/

The Statistical Physics of Real-World Networks

Cimini et al.: https://arxiv.org/abs/1810.05095

#physics #artificialintelligence #neuralnetworks

The Statistical Physics of Real-World Networks

Cimini et al.: https://arxiv.org/abs/1810.05095

#artificialintelligence #neuralnetworks #physics

Eager Execution Enabled

https://colab.research.google.com/github/zaidalyafeai/Notebooks/blob/master/Eager_Execution_Enabled.ipynb

Flow-based Deep Generative Models

By Lilian Weng : https://lilianweng.github.io/lil-log/2018/10/13/flow-based-deep-generative-models.html

#deeplearning #machinelearning #neuralnetworks

AI Driving Olympics Ready for Submissions

Duckietown : https://www.duckietown.org/archives/28465

Leaderboard : https://challenges.duckietown.org/v3/humans/challenges/aido1_LF1-v3/leaderboard

Need data for deep learning?
Skymind's articles have cat memes! And a very comprehensive guide on finding data for deep learning.
https://skymind.ai/wiki/data-for-deep-learning

Free #OpenSource Datasets to Train #DeepLearning Models

Great list of public datasets from Google, Microsoft, Academic Torrents, Github, SkyMind. https://goo.gl/pR2KxG

New book by Christopher Bishop et al.: Model-based Machine Learning

https://mbmlbook.com/ @ArtificialIntelligenceArticles

Cross-Entropy Loss Leads To Poor Margins

paper : https://openreview.net/forum?id=ByfbnsA9Km @ArtificialIntelligenceArticles

Neural Approaches to Conversational AI

Gao et al.: https://arxiv.org/abs/1809.08267

#computation #language #machinelearning

A Brief Introduction to Machine Learning for Engineers

By Osvaldo Simeone : https://arxiv.org/abs/1709.02840

#artificialintelligence #deeplearning #machinelearning @ArtificialIntelligenceArticles