Andrew Fairless – Page 27 – Andrew Fairless, Ph.D.

What I Read: Machines Learn, Teach Basics

By Andrew Fairless on March 21, 2023February 6, 2023

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.”

What I Read: Data Normal

By Andrew Fairless on March 20, 2023February 4, 2023

https://allendowney.blogspot.com/2013/08/are-my-data-normal.html Are your data normal? Hint: no.Allen DowneyWednesday, August 7, 2013 “…what they really want to know (most of the time) is whether a particular distribution is a good modelContinue readingWhat I Read: Data Normal

What I Read: Transformer Inference Optimization

By Andrew Fairless on March 16, 2023January 30, 2023

https://lilianweng.github.io/posts/2023-01-10-inference-optimization/ Large Transformer Model Inference OptimizationLilian WengJanuary 10, 2023 “The extremely high inference cost, in both time and memory, is a big bottleneck for adopting a powerful transformer for solvingContinue readingWhat I Read: Transformer Inference Optimization

What I Read: Optimizing Machine Learning Training Pipelines

By Andrew Fairless on March 15, 2023February 4, 2023

https://medium.com/ntropy-network/bag-of-tricks-for-optimizing-machine-learning-training-pipelines-4f8d5cd3d432 Bag of tricks for optimizing machine learning training pipelinesArseny KravchenkoJan 5 “…we are constantly looking for ways to improve the efficiency of our machine learning pipelines, while keeping theContinue readingWhat I Read: Optimizing Machine Learning Training Pipelines

What I Read: Feature Platforms

By Andrew Fairless on March 14, 2023February 4, 2023

https://huyenchip.com//2023/01/08/self-serve-feature-platforms.html Self-serve feature platforms: architectures and APIsChip HuyenJan 8, 2023 “The last few years saw the maturation of a core component of the MLOps stack that has significantly improved theContinue readingWhat I Read: Feature Platforms

What I Read: Compare Two Ranked Lists

By Andrew Fairless on March 9, 2023January 30, 2023

https://towardsdatascience.com/how-to-objectively-compare-two-ranked-lists-in-python-b3d74e236f6a How to Objectively Compare Two Ranked Lists in PythonKrupesh RaikarJan 5 “Apart from the above movie viewing order disagreement, we are surrounded by examples of comparing lists!…. Ideally, aContinue readingWhat I Read: Compare Two Ranked Lists

What I Read: Data Pipeline Design Patterns

By Andrew Fairless on March 8, 2023January 9, 2023

https://www.startdataengineering.com/post/design-patterns/ Data Pipeline Design Patterns – #1. Data flow patternsStart Data EngineeringDec 11, 2022 “This post will cover the typical data flow design patterns. We will learn about the prosContinue readingWhat I Read: Data Pipeline Design Patterns

What I Read: Modern AI Art

By Andrew Fairless on March 6, 2023January 9, 2023

https://www.quantamagazine.org/the-physics-principle-that-inspired-modern-ai-art-20230105/ The Physics Principle That Inspired Modern AI ArtAnil AnanthaswamyJanuary 5, 2023 “Diffusion models generate incredible images by learning to reverse the process that, among other things, causes ink toContinue readingWhat I Read: Modern AI Art

What I Read: Shapley Values

By Andrew Fairless on March 2, 2023January 9, 2023

https://www.aidancooper.co.uk/how-shapley-values-work/ How Shapley Values WorkAidan CooperDec 31, 2022 “Shapley values… are machine learning explainability techniques…. we will explore how Shapley values work – not using cryptic formulae, but by wayContinue readingWhat I Read: Shapley Values

What I Read: Build vs. Buy, Modern Data Stack

By Andrew Fairless on March 1, 2023January 9, 2023

The Build vs. Buy Guide for the Modern Data Stack The Build vs. Buy Guide for the Modern Data StackNishith AgarwalUpdated December 22, 2022 “There’s been an explosion of solutionsContinue readingWhat I Read: Build vs. Buy, Modern Data Stack

Author: Andrew Fairless