We often buy developer kits with grandiose industrial ambitions, only to leave half the shields sitting in parts drawers gathering dust. Recently, while clearing off my workbench, I grabbed an Elegoo Uno R3 clone paired with a ubiquitous 16×2 LCD keypad shield. The original plan was a quick telemetry display, but old gaming instincts took… Read More: The Project: Dino Runner on 16×2 Character LCD »
Part 5 of 5. Four posts of reasons are enough. This one is about what it looks like when you actually use the thing, and about the name, which people ask about more often than they ask about normalization. Fair enough. One small note first. The command examples below use the usual command line options,… Read More: Using SimurgArray, and the bird behind the name »
An end-to-end rare-disease variant triage platform: a Nextflow pipeline, three execution backends behind one API call, Terraform for two cloud tracks, and a phenotype-driven ranking measured against 10,178 published cases. Including the model metric that collapsed to exactly random once I removed the feature doing all the work.
https://github.com/lynchaos/biapy-hub https://lynchaos-biapy-hub-app-hlcmfj.streamlit.app/ If you have spent your machine learning career optimizing ResNets or YOLO on ImageNet and COCO, here is an inconvenient truth: standard computer vision has spoiled you. In standard computer vision, a batch is usually an RGB triplet where . The pixels are isotropic, the spatial coordinates are Euclidean, the lighting is roughly… Read More: Beyond the 2D Bounding Box: Why Bioimage Deep Learning Is… »
A Raspberry Pi Zero 2 W paired with a Sense HAT V2 runs a fully self-contained, edge-native machine learning weather station with no cloud, GPU, or heavy ML frameworks. The system uses pure NumPy implementations of Recursive Least Squares, Kalman filtering, conformal prediction, and drift detection, staying under 150 MB RAM. The station continuously updates… Read More: I turned a Raspberry Pi into a tiny weather intelligence… »
Repository: github.com/lynchaos/generative-microscopy Why this sketch I wanted to find out whether I could make something that genuinely looked like microscopy footage. Not cells bouncing around a canvas, but Saccharomyces cerevisiae behaving the way it actually behaves under a coverslip, seen through real glass and real light. The sketch began life as a generic n-body attraction… Read More: Building a fake microscope: simulating a yeast wet mount »
I spend most of my working life thinking about what happens inside a stirred tank. Impeller tip speed, shear on the cells, the shape of the vortex that forms when you get the baffling wrong. So when I fell down the rabbit hole of p5.js code golf last week, it was probably inevitable that the… Read More: The Rippled Vortex Ring: Generative Art, and the Infinite Loop… »
What happens when a bioreactor engineer points his state-estimation toolkit at football. Model90 is a statistical forecasting engine for the 2026 World Cup and the major leagues, built on Dixon-Coles Poisson, Elo, xG and a calibrated meta-model. An honest look at how it works and what its Brier score really means.
A Python CLI tool that strips background noise from any video file using ML denoisers — while copying the video stream byte-for-byte. A 6 GB 4K file processes in minutes instead of hours.
A small, cracker-themed block puzzle I cloned and polished for my four-year-old — built in plain vanilla JavaScript with synthesised audio, a Three.js bloom backdrop, and a deliberately forgiving combo system. Free to play, open source on GitHub.