machine learning – Andrew Fairless, Ph.D.

What I Read: VAE

By Andrew Fairless on May 7, 2025February 2, 2025

https://www.rehansheikh.com/blog/vae What the F*** is a VAE?Rehan SheikhJanuary 23, 2025 “A disentangled variational autoencoder aims for each latent dimension… to correspond to a single factor of variation in your dataset.”

What I Read: memorization, novelty

By Andrew Fairless on May 1, 2025February 1, 2025

https://blog.kjamistan.com/how-memorization-happens-novelty.html How memorization happens: Novelty09 Dezember 2024 “…repeated text and images incentivize training data memorization, but that’s not the only training data that machine learning models memorize. Let’s take aContinue readingWhat I Read: memorization, novelty

What I Read: Adaptive LLMs

By Andrew Fairless on April 30, 2025January 30, 2025

https://sakana.ai/transformer-squared Transformer²: Self-Adaptive LLMssakana.aiJanuary 15, 2025 “Imagine a machine learning system that could adjust its own weights dynamically to thrive in unfamiliar settings, essentially illustrating a system that evolves asContinue readingWhat I Read: Adaptive LLMs

What I Read: Tensor Dimensions, Transformers

By Andrew Fairless on April 29, 2025January 28, 2025

https://huggingface.co/blog/not-lain/tensor-dims Mastering Tensor Dimensions in TransformersHafedh HichriJanuary 12, 2025 “Most generative AI models are built using a decoder-only architecture. In this blog post, we’ll explore a simple text generation model,Continue readingWhat I Read: Tensor Dimensions, Transformers

What I Read: pitfalls, building AI

By Andrew Fairless on April 28, 2025January 28, 2025

https://huyenchip.com//2025/01/16/ai-engineering-pitfalls.html Common pitfalls when building generative AI applicationsChip HuyenJan 16, 2025 “As we’re still in the early days of building applications with foundation models, it’s normal to make mistakes. ThisContinue readingWhat I Read: pitfalls, building AI

What I Read: cosine similarity

By Andrew Fairless on April 27, 2025January 28, 2025

https://p.migdal.pl/blog/2025/01/dont-use-cosine-similarity Don’t use cosine similarity carelesslyPiotr Migdał14 Jan 2025 “…we’ll see that blindly applying cosine similarity to vectors can lead us astray. While embeddings do capture similarities, they often reflectContinue readingWhat I Read: cosine similarity

What I Read: AI, HCI

By Andrew Fairless on April 24, 2025January 28, 2025

https://ianarawjo.medium.com/what-ai-engineers-can-learn-from-qualitative-research-methods-in-hci-5b29b9b7465a What AI engineers can learn from qualitative research methods in HCIIan ArawjoJan 9, 2025 “Meet inductive coding and grounded theory, the new bread-and-butter of LLMOps”

What I Read: impossible languages

By Andrew Fairless on April 23, 2025January 18, 2025

https://www.quantamagazine.org/can-ai-models-show-us-how-people-learn-impossible-languages-point-a-way-20250113/ Can AI Models Show Us How People Learn? Impossible Languages Point a Way.Ben Brubaker1/13/25 11:00 AM “Certain grammatical rules never appear in any known language. By constructing artificial languagesContinue readingWhat I Read: impossible languages

What I Read: Statistical Intuitions

By Andrew Fairless on April 22, 2025January 18, 2025

https://arxiv.org/abs/2409.18842 Classical Statistical (In-Sample) Intuitions Don’t Generalize Well: A Note on Bias-Variance Tradeoffs, Overfitting and Moving from Fixed to Random DesignsAlicia Curth27 Sep 2024 “…we show that classical intuitions relatingContinue readingWhat I Read: Statistical Intuitions

What I Read: transfer learning

By Andrew Fairless on April 21, 2025January 18, 2025

https://lunar-joke-35b.notion.site/Transfer-Learning-101-133ba4b6a3fa800e8cede11ee3f1c1cd Transfer Learning 101Himanshu DubeyNov 5, 2024 “Let’s understand Transfer Learning in greater detail.”

Tag: machine learning