February 2021 – Page 5 – Andrew Fairless, Ph.D.

What I Read: Switchback Tests and Randomized Experimentation Under Network Effects

By Andrew Fairless on February 8, 2021January 12, 2021

https://medium.com/@DoorDash/switchback-tests-and-randomized-experimentation-under-network-effects-at-doordash-f1d938ab7c2a Switchback Tests and Randomized Experimentation Under Network Effects at DoorDashDoorDashFeb 14, 2018·12 min readDavid Kastelman, Data Scientist & Raghav Ramesh,Machine Learning Engineer “…given the systemic nature of many ofContinue readingWhat I Read: Switchback Tests and Randomized Experimentation Under Network Effects

What I Read: New Study About Color to Decode ‘The Brain’s Pantone’

By Andrew Fairless on February 8, 2021January 12, 2021

https://www.wired.com/story/a-new-study-about-color-tries-to-decode-the-brains-pantone/ Sara HarrisonScience11.24.2020 07:00 AMA New Study About Color Tries to Decode ‘The Brain’s Pantone’ How do humans perceive color? An NIH experiment finds a way to measure what happensContinue readingWhat I Read: New Study About Color to Decode ‘The Brain’s Pantone’

What I Read: Attention with Performers

By Andrew Fairless on February 7, 2021January 11, 2021

https://ai.googleblog.com/2020/10/rethinking-attention-with-performers.html Rethinking Attention with PerformersFriday, October 23, 2020Posted by Krzysztof Choromanski and Lucy Colwell, Research Scientists, Google Research “To resolve these issues, we introduce the Performer, a Transformer architecture withContinue readingWhat I Read: Attention with Performers

What I Read: Reproducing Deep Double Descent

By Andrew Fairless on February 7, 2021January 11, 2021

https://hippocampus-garden.com/double_descent/ Reproducing Deep Double DescentShion HondaJune 13, 2020 “…you’ve probably heard of bias-variance trade-off… But, do you know that there is a continuation of the U-shaped test risk curve? Surprisingly,Continue readingWhat I Read: Reproducing Deep Double Descent

What I Read: Genes Evolving in Genome’s Junkyard

By Andrew Fairless on February 6, 2021January 11, 2021

https://www.quantamagazine.org/scientists-find-vital-genes-evolving-in-genomes-junkyard-20201116/ Scientists Find Vital Genes Evolving in Genome’s Junkyardby Viviane CallierNovember 16 2020 2:00 PM “Essential genes are often thought to be… evolving only very slowly if at all, becauseContinue readingWhat I Read: Genes Evolving in Genome’s Junkyard

What I Read: Deep Double Descent: Where Bigger Models and More Data Hurt

By Andrew Fairless on February 6, 2021January 11, 2021

https://arxiv.org/abs/1912.02292 Deep Double Descent: Where Bigger Models and More Data HurtPreetum Nakkiran, Gal Kaplun, Yamini Bansal, Tristan Yang, Boaz Barak, Ilya Sutskever “We show that a variety of modern deepContinue readingWhat I Read: Deep Double Descent: Where Bigger Models and More Data Hurt

What I Read: AI for good, think form extraction

By Andrew Fairless on February 5, 2021January 10, 2021

http://jonathanstray.com/to-apply-ai-for-good-think-form-extraction To apply AI for good, think form extractionPosted on October 24, 2020 Author Jonathan Stray “Folks who want to use AI/ML for good generally think of things like buildingContinue readingWhat I Read: AI for good, think form extraction

What I Read: Explainable AI, 2-Stage Approach

By Andrew Fairless on February 5, 2021January 10, 2021

https://www.kdnuggets.com/2020/10/explaining-explainable-ai.html Explaining the Explainable AI: A 2-Stage ApproachBy Amit Dhurandhar, Research Scientist at IBM. “XAI is primarily concerned with understanding or interpreting the decisions made by these opaque or black-boxContinue readingWhat I Read: Explainable AI, 2-Stage Approach

What I Read: “Less than one”-shot learning

By Andrew Fairless on February 4, 2021January 10, 2021

https://www.technologyreview.com/2020/10/16/1010566/ai-machine-learning-with-tiny-data/ Artificial intelligence/Machine learningA radical new technique lets AI learn with practically no data“Less than one”-shot learning can teach a model to identify more objects than the number of examplesContinue readingWhat I Read: “Less than one”-shot learning

What I Read: Architectures for Modern Data Infrastructure

By Andrew Fairless on February 4, 2021January 10, 2021

https://a16z.com/2020/10/15/the-emerging-architectures-for-modern-data-infrastructure/ Emerging Architectures for Modern Data Infrastructureby Matt Bornstein, Martin Casado, and Jennifer Li “We’re now starting to see the rise of massive, complex systems built around data – whereContinue readingWhat I Read: Architectures for Modern Data Infrastructure

Month: February 2021