https://arxiv.org/abs/2206.14486 Beyond neural scaling laws: beating power law scaling via data pruningBen Sorscher, Robert Geirhos, Shashank Shekhar, Surya Ganguli, Ari S. Morcos[Submitted on 29 Jun 2022 (v1), last revised 15
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
What I Learn: SQL, Malloy
https://carlineng.com/?postid=sql-renaissance#blog SQL, Malloy, and the Art of the RenaissanceCarlin Eng02.05.2023 “By allowing sub-tables within resultsets, Malloy results are able to faithfully represent the true dimensionality of the underlying data.”
What I Read: More Flexible Machine Learning
https://www.quantamagazine.org/researchers-discover-a-more-flexible-approach-to-machine-learning-20230207/ Researchers Discover a More Flexible Approach to Machine LearningSteve NadisFebruary 7, 2023 ““Liquid” neural nets, based on a worm’s nervous system, can transform their underlying algorithms on the fly,
What I Read: Machines Learn, Teach Basics
https://www.quantamagazine.org/machines-learn-better-if-we-teach-them-the-basics-20230201/ Machines Learn Better if We Teach Them the BasicsMax G. LevyFebruary 1, 2023 “A wave of research improves reinforcement learning algorithms by pre-training them as if they were human.”