PRML algorithms implemented in Python
Python codes implementing algorithms described in Bishop's book "Pattern Recognition and Machine Learning" : https://github.com/ctgk/PRML
#DeepLearning #MachineLearning #Python

Understanding Self-Training for Gradual Domain Adaptation
Kumar et al.: https://arxiv.org/abs/2002.11361
#ArtificialIntelligence #DeepLearning #MachineLearning

Artificial intelligence has been used for the first time to instantly and accurately measure blood flow, in a study led by UCL and Barts Health NHS Trust

Image: Myocardial blood flow "perfusion map" created and analysed using AI showing an area of the heart receiving a reduced blood supply (arrow) and putting the patient at risk of heart attacks and other adverse events.


https://www.ucl.ac.uk/news/2020/feb/ai-helps-predict-heart-attacks-and-stroke

Severe acute respiratory syndrome coronavirus 2 isolate Wuhan-Hu-1, complete genome
Wu et al.: https://www.ncbi.nlm.nih.gov/nuccore/MN908947.3

Carla: Open-source simulator for autonomous driving research
Github:https://github.com/carla-simulator/carla
Paper:http://proceedings.mlr.press/v78/dosovitskiy17a/dosovitskiy17a.pdf

TensorFlow Quantum

https://www.tensorflow.org/quantum/

Blog on "Architecture Comparison of AlexNet, VGGNet, ResNet, Inception, DenseNet" in Towards Data Science.

https://towardsdatascience.com/architecture-comparison-of-alexnet-vggnet-resnet-inception-densenet-beb8b116866d

Demographic Bias in Biometrics: A Survey on an Emerging Challenge
The main contributions of this article are:
an overview of the topic of algorithmic bias in the context of biometrics,
a comprehensive survey of the existing literature on biometric bias estimation and mitigation,
a discussion of the pertinent technical and social matters, and
an outline of the remaining challenges and future work items, both from technological and social points of view.
https://arxiv.org/pdf/2003.02488.pdf

Yann LeCun

A 14 year old girl born without a left hemisphere exhibits normal language abilities.

This would suggest that language acquisition abilities are not due to some sort of specifically pre-wired circuits in the left hemisphere (where language-related areas are normally found).

https://www.sciencedirect.com/science/article/pii/S0010945220300678

Optimizing JPEG Quantization for Classification Networks. http://arxiv.org/abs/2003.02874

Accelerator-aware Neural Network Design using AutoML. http://arxiv.org/abs/2003.02838

Guided Generative Adversarial Neural Network for Representation Learning and High Fidelit... http://arxiv.org/abs/2003.02836

Machine Learning: A New Approach to Drug Discovery | Daphne Koller | WiDS 2020
https://www.youtube.com/watch?v=V6bSlPNwrKo

Daphne Koller: Machine Learning: A New Approach to Drug Discovery
https://www.youtube.com/watch?v=xz1RWYvHi8g

Better, faster, and cheaper drug discovery with machine learning by AstraZeneca
https://www.youtube.com/watch?v=qH3z5GwccxE

#CarnegieMellon's Delphi research group is extending the forecast of influenza-like illness in anticipation of #COVID19 with the use of statistical #machinelearning.

Learn more →

https://www.ml.cmu.edu/news/news-archive/2020/march/using-machine-learning-cdc-forecasting-flu-covid19-illness.html

https://news.1rj.ru/str/ArtificialIntelligenceArticles

DeepMind, Google’s London-based AI research unit, has published predictions of the structure of proteins associated with SARS-CoV-2, in the hope that they help scientists understand how the new coronavirus functions, and allow for more precise investigation into potential treatments.

The company used its AlphaFold system, which applies machine learning techniques to estimate the physical structure of proteins, to generate the predictions, which it has published without the normal, time consuming, review or verification process for such work.
https://deepmind.com/research/open-source/computational-predictions-of-protein-structures-associated-with-COVID-19
“Knowing a protein’s structure provides an important resource for understanding how it functions, but experiments to determine the structure can take months or longer, and some prove to be intractable,” the researchers wrote in a post accompanying the publication.

“For this reason, researchers have been developing computational methods to predict protein structure from the amino acid sequence.”

https://www.theguardian.com/world/live/2020/mar/05/coronavirus-live-updates-italy-germany-pandemic-europe-uk-us-australia-india-update-latest-news

paper :

https://www.nature.com/articles/s41586-019-1923-7.epdf