machine learning – Page 5 – Andrew Fairless, Ph.D.

What I Read: StandardScaler

By Andrew Fairless on July 24, 2024May 24, 2024

https://www.youtube.com/watch?v=VZxqqH58F5M The StandardScaler is not Standard:probabl. “There is a scaler in scikit-learn called the “StandardScaler”. The name might imply that it is standard or fairly basic., but once you considerContinue readingWhat I Read: StandardScaler

What I Read: Matryoshka Embedding

By Andrew Fairless on July 17, 2024May 6, 2024

https://huggingface.co/blog/matryoshka Introduction to Matryoshka Embedding ModelsTom AarsenJoshuaOmar SansevieroFebruary 23, 2024 “…Kusupati et al. (2022) were inspired to create embedding models whose embeddings could reasonably be shrunk without suffering too muchContinue readingWhat I Read: Matryoshka Embedding

What I Read: LLMs, Open Source

By Andrew Fairless on July 15, 2024May 6, 2024

https://www.aidancooper.co.uk/how-to-beat-proprietary-llms How to Beat Proprietary LLMs With Smaller Open Source ModelsAidan CooperApr 26, 2024 “…we explore the unique advantages of open source LLMs, and how you can leverage them toContinue readingWhat I Read: LLMs, Open Source

What I Read: Hallucinations, AI

By Andrew Fairless on July 9, 2024May 6, 2024

https://www.johndcook.com/blog/2024/03/26/hallucinations-of-ai-science-models/ Hallucinations of AI Science ModelsWayne Joubert3/26/24 11:35 AM “…standard DNN methods applied even to a simple 1-dimensional problem can result in “glitches”: the DNN as a whole matches theContinue readingWhat I Read: Hallucinations, AI

What I Read: Ring Attention

By Andrew Fairless on July 8, 2024April 23, 2024

https://coconut-mode.com/posts/ring-attention Ring Attention ExplainedKilian Haefeli, Simon Zirui Guo, Bonnie Li10 Apr 2024 “Context length in Large Language Models has expanded rapidly…. What if we we could use multiple devices toContinue readingWhat I Read: Ring Attention

What I Read: Kalman Filter

By Andrew Fairless on July 2, 2024April 23, 2024

https://www.youtube.com/watch?v=-DiZGpAh7T4 Kalman Filter – VISUALLY EXPLAINED!Kapil Sachdeva “This tutorial explains the Kalman Filter from Bayesian Probabilistic View and as a special case of Bayesian Filtering.”

What I Read: Data Science, Mostly Dispatch

By Andrew Fairless on July 1, 2024April 23, 2024

https://truetheta.io/concepts/opinions-and-speculations/good-data-science-is-mostly-dispatch Good Data Science is Mostly DispatchDJ RichOctober 27, 2023 “By good data science is mostly dispatch, I mean most of what explains a job well done is the choiceContinue readingWhat I Read: Data Science, Mostly Dispatch

What I Read: Don’t put notebooks into production

By Andrew Fairless on June 27, 2024April 23, 2024

https://martinfowler.com/articles/productize-data-sci-notebooks.html Don’t put data science notebooks into productionDavid Johnston18 November 2020 “…the discussion of how to productionize data science notebooks is missing the point. The goal should be to empowerContinue readingWhat I Read: Don’t put notebooks into production

What I Read: Flow Matching

By Andrew Fairless on June 26, 2024April 23, 2024

https://mlg.eng.cam.ac.uk/blog/2024/01/20/flow-matching.html An introduction to Flow MatchingTor Fjelde, Emile Mathieu, Vincent Dutordoir “Flow matching (FM) is a recent generative modelling paradigm which has rapidly been gaining popularity in the deep probabilisticContinue readingWhat I Read: Flow Matching

What I Read: How Machines ‘Grok’ Data

By Andrew Fairless on June 25, 2024April 23, 2024

https://www.quantamagazine.org/how-do-machines-grok-data-20240412 How Do Machines ‘Grok’ Data?Anil Ananthaswamy4/12/24 “By apparently overtraining them, researchers have seen neural networks discover novel solutions to problems.”

Tag: machine learning