https://www.quantamagazine.org/cryptographers-show-how-to-hide-invisible-backdoors-in-ai-20230302/ In Neural Networks, Unbreakable Locks Can Hide Invisible DoorsBen BrubakerMarch 2, 2023 “Cryptographers have shown how perfect security can undermine machine learning models.”
What I Read: Bloom filter
https://luminousmen.com/post/building-a-bloom-filter Building a Bloom filterluminousmen “In this post, we will explore the Bloom filter — a data structure that is ingenious in its simplicity and elegant in its design.”
What I Read: Predict Distributions
https://towardsdatascience.com/a-new-way-to-predict-probability-distributions-e7258349f464?gi=3201d118e909 A New Way to Predict Probability DistributionsExploring multi-quantile regression with CatboostHarrison HoffmanFeb 14 “Until recently, the main disadvantage of quantile regression was that one model had to be trained
What I Read: Geometric Deep Learning
https://thegradient.pub/towards-geometric-deep-learning/ Towards Geometric Deep LearningMichael Bronstein18.Feb.2023 “Geometric Deep Learning is an umbrella term for approaches considering a broad class of ML problems from the perspectives of symmetry and invariance.”
What I Read: Teach Computers Math
https://www.quantamagazine.org/to-teach-computers-math-researchers-merge-ai-approaches-20230215/ To Teach Computers Math, Researchers Merge AI ApproachesKevin HartnettFebruary 15, 2023 “Large language models still struggle with basic reasoning tasks. Two new papers that apply machine learning to math