Growing Neural Cellular Automata
Differentiable Model of Morphogenesis
Mordvintsev et al.: https://distill.pub/2020/growing-ca/
#ArtificialIntelligence #DeepLearning #MachineLearning

Self-training with Noisy Student improves ImageNet classification
Xie et al.: https://arxiv.org/abs/1911.04252
Code: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
#ArtificielIntelligence #DeepLearning #MachineLearning

Learning structure (Dx-Rx) in medical records data and using that to improve prediction accuracy.

Learning the Graphical Structure of Electronic Health Records withGraph Convolutional Transformer

code

https://github.com/Google-Health/records-research/tree/master/graph-convolutional-transformer

paper
https://arxiv.org/pdf/1906.04716.pdf

Deep Learning by Alexander Amini 2020

https://www.youtube.com/watch?v=njKP3FqW3Sk

Andrew ng :

Consumer internet companies with 1B+ users have popularized Big Data. But industries like manufacturing, agriculture & healthcare need AI to work on Small Data. This article by Landing AI's Alejandro Betancourt gives a good overview of emerging Small Data techniques. https://www.industryweek.com/technology-and-iiot/digital-tools/article/21122846/making-ai-work-with-small-data

A Probabilistic Formulation of Unsupervised Text Style Transfer
He et al.: https://arxiv.org/abs/2002.03912
#DeepLearning #GenerativeModel #MachineLearning

Growing Neural Cellular Automata
https://distill.pub/2020/growing-ca/

ARIES is a networked software technology that redefines ecosystem service assessment and valuation for decision-making. The ARIES approach to mapping natural capital, natural processes, human beneficiaries, and service flows to society is a powerful new way to visualize, value, and manage the ecosystems on which the human economy and well-being depend.
https://www.youtube.com/watch?v=vsWGkMBpI9Y

On the Morality of Artificial Intelligence
Alexandra Luccioni, Yoshua Bengio : https://arxiv.org/abs/1912.11945
#Society #AIEthics #ArtificialIntelligence

Mila AI Institute is looking for interns to help on applied Machine Learning projects in different AI for Humanity areas (health, environment, humanitarian aid,etc.)

The ideal candidate would have a working knowledge of AI/ML and would be willing to work on projects supervised by mentors at Mila and supported by domain experts.

The goal of these internships is not to publish scientific papers, but to design and deploy ML solutions that can make meaningful impact on problems that are important for society.

Apply here: https://docs.google.com/forms/d/e/1FAIpQLSflOoGyOLhw02UmBCwFTZZMKcuojw33lVQT_m3p0t2RSzeP1A/viewform

Different languages use very different approaches to construct meaning
and to understand the many ways languages express meaning

TyDi QA: A Multilingual Question Answering Benchmark https://ai.googleblog.com/2020/02/tydi-qa-multilingual-question-answering.html

Machine Learning Department, Carnegie Mellon University

https://blog.ml.cmu.edu/

Self-Distillation Amplifies Regularization in Hilbert Space
https://arxiv.org/abs/2002.05715v1

Yann lecun

Very impressive speed-up of physics simulations using ConvNets emulators obtained through architecture search.
Results on 10 applications in climate modeling, plasma, etc.

https://arxiv.org/abs/2001.08055

How to implement a YOLO (v3) object detector from scratch in PyTorch: Part 1
Blog by Ayoosh Kathuria: https://blog.paperspace.com/how-to-implement-a-yolo-object-detector-in-pytorch/
#ArtificialIntelligence #ComputerVision #DeepLearning #MachineLearning #PatternRecognition