Handbook of Graphical Models
Marloes Maathuis, Mathias Drton, Ste􏰆en Lauritzen and Martin Wainwright : https://stat.ethz.ch/~maathuis/papers/Handbook.pdf
#Handbook #GraphicalModels

Causal Inference: What If
Miguel A. Hernán, James M. Robins : https://cdn1.sph.harvard.edu/wp-content/uploads/sites/1268/2019/11/ci_hernanrobins_10nov19.pdf
#CausalInference

Breast Histopathology Images Dataset
Download: https://www.kaggle.com/paultimothymooney/breast-histopathology-images

A tutorial to implement state-of-the-art NLP models with Fastai for Sentiment Analysis
Maximilien Roberti : https://towardsdatascience.com/fastai-with-transformers-bert-roberta-xlnet-xlm-distilbert-4f41ee18ecb2
#FastAI #NLP #Transformers

Pre-Debate Material :
Recurrent Independent Mechanisms
Anirudh Goyal, Alex Lamb, Jordan Hoffmann, Shagun Sodhani, Sergey Levine, Yoshua Bengio, Bernhard Schölkopf : https://arxiv.org/abs/1909.10893
#MachineLearning #Generalization #ArtificialIntelligence

Pre-Debate Material :
Meta transfer learning for factorizing representations and knowledge for AI - Yoshua Bengio : https://youtu.be/CHnJYBpMjNY
#AIDebate #MontrealAI

A decade ago we weren’t sure neural nets could ever deal with language.

Now the latest AI models crush language benchmarks faster than we can come up with language benchmarks.

Far from having an AI winter, we are having a second AI spring.

The first AI spring is of course ImageNet. Created by Dr. Fei Fei Li and team in 2009, it was the first large scale image classification problem for photos instead of handwriting and thumbnails.

In 2012, AlexNet using GPUs took 1st place. In 2015, ResNet reached human performance.

In the years that followed neural nets made strong progress on voice recognition and machine translation.

Baidu’s Deep Speech 2 recognized spoken Chinese on-par with humans. Google’s Neural-Machine-Translation beat existing phrase-based translation system by 60%.

In language understanding, neural nets did well in single tasks such as WikiQA, TREC, and SQuAD but it wasn’t clear they could master a range of tasks like humans.

Thus GLUE was created—a set of 9 diverse language tasks that hopefully would keep researchers busy for years.
It took six years for neural nets to catch up to human performance in ImageNet.

Transformer based neural nets (BERT, GPT) beat human performance in GLUE in less than one year.

Progress in language-understanding was so rapid, the authors of GLUE was forced to create a new version of the benchmark “SuperGLUE” in 2019.

SuperGlue is HARD, far harder than a naive Turing Test. Just look at these prompts.

Will SuperGLUE stand the test of time? It appears not. Six months in and the Google T5 model is within 1% of human performance.

Neural nets are beating language benchmarks faster than benchmarks can be created.

Yet first hand experience contradicts this progress—Alexa/Siri/Google still lack basic common sense.

Why? Is it a matter of time to deployment or are diverse human questions just much harder?

See:

Google's T5 (Text-To-Text Transfer Transformer) language model set new record and gets very close to human on SuperGLUE benchmark.

https://bit.ly/2XQkKxO

Paper: https://arxiv.org/abs/1910.10683
Code: https://github.com/google…/text-to-text-transfer-transformer

Pre-Debate Material :
WSAI Americas 2019 - Yoshua Bengio - Moving beyond supervised deep learning : https://youtu.be/0GsZ_LN9B24
#AIDebate #MontrealAI

Meta-transfer learning for factorizing representations, casual graphs and knowledge for AI
Discover causal representation
Beyond i.i.d, independent mechanism, and single variable intervention
Causal structure and knowledge factorization, correct causal -> faster adaptation & better transfer
Hindrances are not problems, they are features.
Meta-optimizer: online learning errors promote changing in structural parameters (i.e. the network architecture)
Complex models and small data could generalize will under the right causal structure!
The consciousness prior
The future: the brain has different learning rate for different sections => fast/slow weight, long/short term parameters, causal without direct intervention but passive observation (like a child learning)
Paper:
https://arxiv.org/pdf/1901.10912.pdf
https://slideslive.com/38915855

Best Releases and Papers from OpenAI in 2019 So Far
https://opendatascience.com/best-releases-and-papers-from-openai-in-2019-so-far/

Top 100 Neuroscience Blogs And Websites For Neuroscientists in 2019

https://blog.feedspot.com/neuroscience_blogs/

@ArtificialIntelligenceArticles

The first video GAN with sparse input release by Facebook recently
Paper: https://research.fb.com/publications/deepfovea-neural-reconstruction-for-foveated-rendering-and-video-compression-using-learned-statistics-of-natural-videos/
Github: https://github.com/facebookresearch/DeepFovea
DeepFovea can decrease the number of computing resources needed for rendering by as much as 10-14x while any image differences remain imperceptible to the human eye.

An Epidemic of AI Misinformation
Gary Marcus : https://thegradient.pub/an-epidemic-of-ai-misinformation/
#ArtificialIntelligence #DeepLearning #MachineLearning

Deep Learning

[http://web.stanford.edu/class/cs230/](http://web.stanford.edu/class/cs230/)

[ Natural Language Processing ]

CS 124: From Languages to Information (LINGUIST 180, LINGUIST 280)

[http://web.stanford.edu/class/cs124/](http://web.stanford.edu/class/cs124/)

CS 224N: Natural Language Processing with Deep Learning (LINGUIST 284)

[http://web.stanford.edu/class/cs224n/](http://web.stanford.edu/class/cs224n/)

CS 224U: Natural Language Understanding (LINGUIST 188, LINGUIST 288)

[http://web.stanford.edu/class/cs224u/](http://web.stanford.edu/class/cs224u/)

CS 276: Information Retrieval and Web Search (LINGUIST 286)

[http://web.stanford.edu/class/cs](http://web.stanford.edu/class/cs224u/)276

[ Computer Vision ]
CS 131: Computer Vision: Foundations and Applications

http://[cs131.stanford.edu](http://cs131.stanford.edu/)

CS 205L: Continuous Mathematical Methods with an Emphasis on Machine Learning

[http://web.stanford.edu/class/cs205l/](http://web.stanford.edu/class/cs205l/)

CS 231N: Convolutional Neural Networks for Visual Recognition

[http://cs231n.stanford.edu/](http://cs231n.stanford.edu/)

CS 348K: Visual Computing Systems

[http://graphics.stanford.edu/courses/cs348v-18-winter/](http://graphics.stanford.edu/courses/cs348v-18-winter/)

[ Others ]

CS224W: Machine Learning with Graphs([Yong Dam Kim](https://www.facebook.com/yongdam.kim) )

[http://web.stanford.edu/class/cs224w/](http://web.stanford.edu/class/cs224w/)


CS 273B: Deep Learning in Genomics and Biomedicine (BIODS 237, BIOMEDIN 273B, GENE 236)

[https://canvas.stanford.edu/courses/51037](https://canvas.stanford.edu/courses/51037)

CS 236: Deep Generative Models

[https://deepgenerativemodels.github.io/](https://deepgenerativemodels.github.io/)

CS 228: Probabilistic Graphical Models: Principles and Techniques

[https://cs228.stanford.edu/](https://cs228.stanford.edu/)

CS 337: Al-Assisted Care (MED 277)

[http://cs337.stanford.edu/](http://cs337.stanford.edu/)

CS 229: Machine Learning (STATS 229)

[http://cs229.stanford.edu/](http://cs229.stanford.edu/)

CS 229A: Applied Machine Learning

[https://cs229a.stanford.edu](https://cs229a.stanford.edu/)

CS 234: Reinforcement Learning

http://[s234.stanford.edu](http://cs234.stanford.edu/)

CS 221: Artificial Intelligence: Principles and Techniques

[https://stanford-cs221.github.io/autumn2019/](https://stanford-cs221.github.io/autumn2019/)

Hamiltonian Graph Networks with ODE Integrators
Sanchez-Gonzalez et al.: https://arxiv.org/abs/1909.12790
#ArtificialIntelligence #Hamiltonian #GraphNetworks

Bayesian Deep Learning Benchmarks
Oxford Applied and Theoretical Machine Learning Group : https://github.com/OATML/bdl-benchmarks
#Bayesian #Benchmark #DeepLearning

We’ve completed the first fastMRI image reconstruction challenge to spur development of new AI techniques to make scans 10x faster. Congratulations to the top entrants, who’ve been invited to present at the Medical Imaging Meets NeurIPS workshop!

https://ai.facebook.com/blog/results-of-the-first-fastmri-image-reconstruction-challenge

We just released our #NeurIPS2019 Multimodal Model-Agnostic Meta-Learning (MMAML) code for learning few-shot image classification, which extends MAML to multimodal task distributions (e.g. learning from multiple datasets). The code contains #PyTorch implementations of our model and two baselines (MAML and Multi-MAML) as well as the scripts to evaluate these models to five popular few-shot learning datasets: Omniglot, Mini-ImageNet, FC100 (CIFAR100), CUB-200-2011, and FGVC-Aircraft.

Code: https://github.com/shaohua0116/MMAML-Classification

Paper: https://arxiv.org/abs/1910.13616

#NeurIPS #MachineLearning #ML #code

Mathematics for Machine Learning

Free Download Printed Book Cambridge University Press
https://mml-book.github.io/


#artificialintelligence #AI #Mathematics #calculus #linearalgebra #deeplearning #machinelearning