https://www.quantamagazine.org/researchers-glimpse-how-ai-gets-so-good-at-language-processing-20220414/ Researchers Gain New Understanding From Simple AIMordechai RorvigStaff WriterApril 14, 2022 “Language processing programs are notoriously hard to interpret, but smaller versions can provide important insights into how they
What I Read: forecasting, quantile functions
https://www.amazon.science/blog/improving-forecasting-by-learning-quantile-functions Improving forecasting by learning quantile functionsBy Youngsuk Park, François-Xavier AubetMarch 31, 2022 “Learning the complete quantile function, which maps probabilities to variable values, rather than building separate models for
What I Read: Generalization of SGD
https://www.quantamagazine.org/machine-learning-reimagines-the-building-blocks-of-computing-20220315/ Machine Learning Reimagines the Building Blocks of ComputingNick ThiemeContributing WriterMarch 15, 2022 “Traditional algorithms power complicated computational tools like machine learning. A new approach, called algorithms with predictions, uses
What I Read: Deep Learning From First Principles
https://horace.io/brrr_intro.html Making Deep Learning Go Brrrr From First PrinciplesHorace He “So, you want to improve the performance of your deep learning model. How might you approach such a task?”
What I Read: Brain-Inspired Hardware
https://www.quantamagazine.org/ai-overcomes-stumbling-block-on-brain-inspired-hardware-20220217/ AI Overcomes Stumbling Block on Brain-Inspired HardwareAllison WhittenContributing WriterFebruary 17, 2022 “Algorithms that use the brain’s communication signal can now work on analog neuromorphic chips, which closely mimic our
What I Read: Will Transformers Take Over Artificial Intelligence?
https://www.quantamagazine.org/will-transformers-take-over-artificial-intelligence-20220310/ Will Transformers Take Over Artificial Intelligence?A simple algorithm that revolutionized how neural networks approach language is now taking on vision as well. It may not stop there.Stephen OrnesContributing WriterMarch
What I Read: Why Bigger Neural Networks Do Better
https://www.quantamagazine.org/computer-scientists-prove-why-bigger-neural-networks-do-better-20220210/ Computer Scientists Prove Why Bigger Neural Networks Do BetterMordechai RorvigStaff WriterFebruary 10, 2022 “Two researchers show that for neural networks to be able to remember better, they need far
What I Read: Researchers Build AI That Builds AI
https://www.quantamagazine.org/researchers-build-ai-that-builds-ai-20220125/ Researchers Build AI That Builds AIAnil AnanthaswamyJanuary 25, 2022“By using hypernetworks, researchers can now preemptively fine-tune artificial neural networks, saving some of the time and expense of training.”
What I Read: Visual Explanation of Classifiers
https://ai.googleblog.com/2022/01/introducing-stylex-new-approach-for.html Introducing StylEx: A New Approach for Visual Explanation of ClassifiersTuesday, January 18, 2022Posted by Oran Lang and Inbar Mosseri, Software Engineers, Google Research“Previous approaches for visual explanations of classifiers…