InsuLearner
Open-source algorithms and tools for computing insulin pump settings, with practical integrations for Tidepool and Nightscout data.
Open ProjectAI + Data Science
Work in healthcare, signal processing, machine listening, and ecological audio.
Background
Twenty years of applied machine learning and signal processing across healthcare, music technology, ecological audio, and recommendation systems. Work has included FDA-facing insulin dosing algorithms at Tidepool, large-scale machine listening at Gracenote, AI bird detection with the U.S. National Park Service, and recommendation systems at Change.org. Published at ISMIR and ACM SIGIR; multiple patents filed and granted.
NPS Acoustic Discovery
AI bird-detection tooling for ecological recordings developed with the U.S. National Park Service.
Open Project
Gracenote Mood 2.0
Archive of my work on deep-learning-based mood classification and music intelligence systems at scale.
Open Project
Precision-Recall Visualization Tool
Interactive explainer for thresholding, tradeoffs, and classification thinking.
Open ProjectNotes
- How I Calculate My Son's Insulin Pump Settings with Machine Learning (origin of the project)
- InsuLearner Software for Computing Insulin Pump Settings (technical overview)
- InsuLearner + Insulearner Web: Nightscout Update (current release notes)