PinnedSean GahaganSeries Recap: A High-Level Understanding of Machine LearningThis note shares a final recap of my series of notes on the different topics from Andrew Ng’s Machine Learning course. I hope that these…Oct 21, 2022Oct 21, 2022
Sean GahaganIntuition on Fine-Tuning LLMsIn this note, we’ll discuss fine-tuning as an approach to training a LLM to better follow instructions for a specific task or set of tasks…Just nowJust now
Sean GahaganAdjusting LLM Outputs: Inference Configuration ParametersIn this note, we’ll discuss a handful of model parameters that influence a LLM’s outputs, but are distinct from model training/development…Sep 9Sep 9
Sean GahaganPrompt Engineering & In-Context LearningIn this note, we’ll look at ways of improving the performance of a LLM by changing the prompt, and without changing the underlying model.Sep 7Sep 7
Sean GahaganIntuition on How Transformers WorkPrior to 2017, the state of the art for GenAI models was an architecture called recurrent neural networks (RNNs), but after the the…Sep 5Sep 5
Sean GahaganWhat is Generative AI? + Key GenAI VocabularyA few months ago, I completed the Generative AI with Large Language Models course provided by deeplearning.ai and Amazon Web Services. To…Sep 2Sep 2
Sean GahaganDeep Learning in Practice: Building the DrawMoji ModelAfter earning deeplearning.ai’s Deep Learning Specialization certifications in 2020, I wanted to put my knowledge into practice by building…Feb 25, 2023Feb 25, 2023
Sean GahaganBuilding Intuition around High-Dimensional Space in Deep LearningIn my recap of Prof. Andrew Ng’s lectures from the Stanford Machine Learning course, I shared that you can imagine supervised learning as…Dec 10, 2022Dec 10, 2022
Sean GahaganA High-Level Introduction to Dimensionality Reduction and Principal Component Analysis (PCA)My last note shared how to prioritize which parts of a machine learning system are most important to work on using ceiling analysis. This…Oct 21, 2022Oct 21, 2022
Sean GahaganCeiling Analysis for Prioritizing Work on ML SystemsMy last note shared how a system of machine learning models can be used to identify and classify text within an image in optical character…Oct 21, 2022Oct 21, 2022