2022 – Page 4 – Andrew Fairless, Ph.D.

What I Read: Backpropagation, Chain Rule

By Andrew Fairless on October 13, 2022September 9, 2022

Backpropagation ≠ Chain Rule Backpropagation ≠ Chain RulePosted on December 16, 2021by Lunjia Hu “…a common belief that “backpropagation is just applying the chain rule repeatedly”. While this is in aContinue readingWhat I Read: Backpropagation, Chain Rule

What I Read: AI, Limits, Language

By Andrew Fairless on October 12, 2022September 9, 2022

https://www.noemamag.com/ai-and-the-limits-of-language/AI And The Limits Of LanguageBy Jacob Browning and Yann LeCunAugust 23, 2022 “An artificial intelligence system trained on words and sentences alone will never approximate human understanding.”

What I Read: Snowflake Query Optimizer

By Andrew Fairless on October 11, 2022September 27, 2022

https://teej.ghost.io/understanding-the-snowflake-query-optimizer/ Understanding the Snowflake Query OptimizerSep 18, 2022 “The job of a query optimizer is to reduce the cost of queries without changing what they do…. Query optimizers aren’t uniqueContinue readingWhat I Read: Snowflake Query Optimizer

What I Read: When use Bayesian optimization

By Andrew Fairless on October 10, 2022September 9, 2022

https://medium.com/@eduardogarrido90/when-do-i-need-to-use-bayesian-optimization-bo-series-i-50531ba6952d When do I need to use Bayesian optimization? (BO series I)Eduardo C. Garrido MerchánAug 22 “When do I need to use Bayesian optimization? And the answer is suprising, becauseContinue readingWhat I Read: When use Bayesian optimization

What I Read: Emergent Features

By Andrew Fairless on October 6, 2022August 22, 2022

LLM.int8() and Emergent Features LLM.int8() and Emergent Features2022-08-17 by Tim Dettmers “…I use advanced quantization methods to achieve no performance degradation transformer inference at scale that makes large models moreContinue readingWhat I Read: Emergent Features

What I Read: Self-Taught AI, Brain

By Andrew Fairless on October 4, 2022August 22, 2022

https://www.quantamagazine.org/self-taught-ai-shows-similarities-to-how-the-brain-works-20220811/ Self-Taught AI Shows Similarities to How the Brain WorksAnil AnanthaswamyContributing WriterAugust 11, 2022 “Self-supervised learning allows a neural network to figure out for itself what matters. The process mightContinue readingWhat I Read: Self-Taught AI, Brain

What I Read: Comparing quantiles at scale

By Andrew Fairless on October 3, 2022August 22, 2022

https://engineering.atspotify.com/2022/03/comparing-quantiles-at-scale-in-online-a-b-testing/ Comparing quantiles at scale in online A/B-testingMarch 23, 2022Published by Mårten Schultzberg (Senior Data Scientist) and Sebastian Ankargren (Data Scientist) “…we have been able to reduce the computational complexityContinue readingWhat I Read: Comparing quantiles at scale

What I Read: Testing Firefox, machine learning

By Andrew Fairless on September 29, 2022August 22, 2022

https://hacks.mozilla.org/2020/07/testing-firefox-more-efficiently-with-machine-learning/ Testing Firefox more efficiently with machine learningBy Andrew Halberstadt, Marco CastelluccioPosted on July 9, 2020 “Even with all of these optimizations our CI still runs around 10 compute yearsContinue readingWhat I Read: Testing Firefox, machine learning

What I Read: Robot Learned, Scraping Web

By Andrew Fairless on September 28, 2022August 22, 2022

https://www.wired.com/story/google-robot-learned-to-take-orders-by-scraping-the-web/ Google’s New Robot Learned to Take Orders by Scraping the WebWill KnightBusinessAug 16, 2022 10:00 AM “The machine learning technique that taught notorious text generator GPT-3 to write canContinue readingWhat I Read: Robot Learned, Scraping Web

What I Read: Concept Drift Without Labeled Data

By Andrew Fairless on September 26, 2022August 22, 2022

https://concept-drift.fastforwardlabs.com/ Inferring Concept Drift Without Labeled DataFF22Aug 2021 “…we explore broadly applicable approaches for dealing with concept drift when labeled data is not readily accessible. We’ll start by defining whatContinue readingWhat I Read: Concept Drift Without Labeled Data

Year: 2022