How Machines Actually Learn
It's not magic, it's science: a model guesses, checks how wrong it was, and adjusts. Walked through with nothing but high-school algebra.
Five things in this room go somewhere.Five places to start.
I work with data for a living and build systems around it — pipelines that run without being watched, models that answer a question worth asking, and the engineering that makes both usable by someone other than me.
Most of what is here is either finished, in progress, or did not work. All three are labelled.
A tool that indexes academic papers and extracts their structure — authors, institutions, methodology, and materials — using an LLM.
A Flask web app that classifies foot and ankle X-rays and overlays Grad-CAM heatmaps to show what the model is looking at.
Last changed 2026-09
Empty bench
Experiments show up here.
It's not magic, it's science: a model guesses, checks how wrong it was, and adjusts. Walked through with nothing but high-school algebra.
You don't need a separate BI tool to explore data interactively — ipywidgets gets you dropdowns, buttons, and live updating charts right inside the notebook.
If you have messy data, a model idea, or reporting that eats someone's week, tell me about it.
Work with me