classification – Andrew Fairless, Ph.D.

What I Read: Model Calibration

By Andrew Fairless on June 2, 2025February 22, 2025

Understanding Model Calibration: A Gentle Introduction & Visual Exploration Maja PavlovicFeb 11, 2025 “Calibration makes sure that a model’s estimated probabilities match real-world outcomes… if a weather forecasting model predictsContinue readingWhat I Read: Model Calibration

What I Read: Reasoning LLMs

By Andrew Fairless on May 21, 2025February 22, 2025

https://magazine.sebastianraschka.com/p/understanding-reasoning-llms Understanding Reasoning LLMsSebastian Raschka, PhDFeb 05, 2025 “This article describes the four main approaches to building reasoning models, or how we can enhance LLMs with reasoning capabilities.”

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: Classifying pdfs

By Andrew Fairless on November 21, 2024August 26, 2024

https://snats.xyz/pages/articles/classifying_a_bunch_of_pdfs.html Classifying all of the pdfs on the internetSantiago Pedroza2024-08-18 “How would you classify all the pdfs in the internet? Well, that is what I tried doing this time.”

What I Read: Tool Retrieval, RAG

By Andrew Fairless on November 20, 2024August 26, 2024

https://jxnl.co/writing/2024/08/21/trade-off-tool-selection Optimizing Tool Retrieval in RAG Systems: A Balanced ApproachJason Liu2024/08/21 “When it comes to Retrieval-Augmented Generation (RAG) systems, one of the key challenges is deciding how to select andContinue readingWhat I Read: Tool Retrieval, RAG

What I Read: Labeling, Uncertainty Sampling

By Andrew Fairless on July 30, 2024May 24, 2024

https://code.groundlight.ai/python-sdk/blog/active-learning Reducing Data Labeling Costs with Uncertainty SamplingTed SandlerMay 15, 2024Senior Applied Scientist “With active learning, only informative images are prioritized for review, making it possible to label small aContinue readingWhat I Read: Labeling, Uncertainty Sampling

What I Read: Sampling Text Generation

By Andrew Fairless on March 19, 2024February 5, 2024

https://huyenchip.com//2024/01/16/sampling.html Sampling for Text GenerationChip Huyen1/15/24 “ML models are probabilistic…. This probabilistic nature makes AI great for creative tasks…. However, this probabilistic nature also causes inconsistency and hallucinations. It’s fatalContinue readingWhat I Read: Sampling Text Generation

What I Read: Confidence intervals, balanced accuracy

By Andrew Fairless on March 14, 2024January 25, 2024

https://code.groundlight.ai/python-sdk/blog/confidence-intervals-for-balanced-accuracy Tales from the Binomial Tail: Confidence intervals for balanced accuracyTed SandlerSenior Applied Scientist at GroundlightLeo DiracCTO and Co-founder at GroundlightJanuary 16, 2024 “…we put careful thought into measuring theContinue readingWhat I Read: Confidence intervals, balanced accuracy

What I Read: Salmon, Loop

By Andrew Fairless on March 5, 2024January 25, 2024

https://thegradient.pub/salmon-in-the-loop/ Salmon in the LoopKevin McCraney12/16/23 12:00 PM “Building a computer vision system for a highly-regulated industry, such as hydropower utilities, can be a challenging task due to the needContinue readingWhat I Read: Salmon, Loop

What I Read: Inducing hierarchy for multi-class classification

By Andrew Fairless on February 22, 2024January 7, 2024

https://arxiv.org/abs/2102.10263 Inducing a hierarchy for multi-class classification problemsHayden S. Helm, Weiwei Yang, Sujeeth Bharadwaj, Kate Lytvynets, Oriana Riva, Christopher White, Ali Geisa, Carey E. Priebe “In applications where categorical labelsContinue readingWhat I Read: Inducing hierarchy for multi-class classification

Tag: classification