Andrew Fairless – Page 41 – Andrew Fairless, Ph.D.

What I Read: Data Distribution Shifts

By Andrew Fairless on April 6, 2022March 12, 2022

https://huyenchip.com//2022/02/07/data-distribution-shifts-and-monitoring.html Data Distribution Shifts and MonitoringChip HuyenFebruary 7 2022 12:00 AM “…deploying a model isn’t the end of the process. A model’s performance degrades over time in production. Once aContinue readingWhat I Read: Data Distribution Shifts

What I Read: Musings on typicality

By Andrew Fairless on April 5, 2022March 12, 2022

https://benanne.github.io/2020/09/01/typicality.html Musings on typicalitySeptember 01, 2020Sander Dieleman “…typicality is a concept worth understanding. It sheds light on why beam search doesn’t work for autoregressive models of images, audio and video;Continue readingWhat I Read: Musings on typicality

What I Read: Scale Real-time Data Infrastructure

By Andrew Fairless on April 4, 2022February 3, 2022

https://zhenzhongxu.com/the-four-innovation-phases-of-netflixs-trillions-scale-real-time-data-infrastructure-2370938d7f01 The Four Innovation Phases of Netflix’s Trillions Scale Real-time Data InfrastructureZhenzhong Xu2/1/2022“I think it’s a perfect time to summarize my learnings building the real-time data infrastructure at Netflix. IContinue readingWhat I Read: Scale Real-time Data Infrastructure

What I Read: Researchers Build AI That Builds AI

By Andrew Fairless on March 30, 2022February 3, 2022

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: Statistical Critiques That Don’t Quite Work

By Andrew Fairless on March 29, 2022February 3, 2022

https://nickch-k.github.io/SomeThoughts/posts/2022-01-23-overdebunked/ Overdebunked! Six Statistical Critiques That Don’t Quite WorkWhen healthy skepticism of statistics turns into worse statistics (and an excuse).Nick Huntington-KleinJan. 23, 2022 “Skepticism about statistics is good. However, justContinue readingWhat I Read: Statistical Critiques That Don’t Quite Work

What I Read: Experiment without the wait

By Andrew Fairless on March 28, 2022February 3, 2022

https://medium.com/pinterest-engineering/experiment-without-the-wait-speeding-up-the-iteration-cycle-with-offline-replay-experimentation-7a4a95fa674b Pinterest EngineeringJan 18Experiment without the wait: Speeding up the iteration cycle with Offline Replay ExperimentationMaxine Qian | Data Scientist, Experimentation and Metric Sciences“Online experimentation is often used to evaluateContinue readingWhat I Read: Experiment without the wait

What I Read: Visual Explanation of Classifiers

By Andrew Fairless on March 23, 2022February 3, 2022

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…Continue readingWhat I Read: Visual Explanation of Classifiers

What I Read: Principles that Boost Innovation

By Andrew Fairless on March 22, 2022February 3, 2022

https://www.pymc-labs.io/blog-posts/labs-principles/ My Journey Building PyMC Labs: Five Principles from Open Source that Boost Innovation at any Company5 organizational principles that foster innovation at PyMC LabsAuthored by Thomas Wiecki on 2022-01-10“IContinue readingWhat I Read: Principles that Boost Innovation

What I Read: ML model drift in production

By Andrew Fairless on March 21, 2022January 20, 2022

https://towardsdatascience.com/my-data-drifted-whats-next-how-to-handle-ml-model-drift-in-production-78719ef007b1 “My data drifted. What’s next?” How to handle ML model drift in production.An introductory overview of the possible steps.Elena SamuylovaDec 1, 2021 ““I have a model in production, andContinue readingWhat I Read: ML model drift in production

What I Read: Aristotle, Deep Learning

By Andrew Fairless on March 17, 2022March 12, 2022

https://thegradient.pub/how-aristotle-is-fixing-deep-learnings-flaws/ How Aristotle is Fixing Deep Learning’s FlawsPaul J. Blazek17.Feb.2022 “…Aristotle’s logic still stands strong, poignantly describing the building blocks of human reasoning. Yet many of the key ingredients describedContinue readingWhat I Read: Aristotle, Deep Learning

Author: Andrew Fairless