An Engineer's musings
Notes on building software — languages, tooling, and how things work under the hood, with the occasional tangent. Kotlin and the JVM show up often, but each post is really just a careful look at an idea worth understanding.
Latest posts
-
Capstone: Teach the Computer (and Use AI Wisely) The grand finale. Train your own model end to end, present how well it works, and have the most important conversation in AI: how to use it responsibly. -
Test It, See the Mistakes, Make It Better A great score isn't the end. Look at the actual digits your AI got wrong, understand why, and try simple changes to push the accuracy higher. -
Train an Image Recognizer Teach a model to read handwritten digits. Same recipe as the penguins — but now the features are pixels, and your AI learns to recognize images. -
Pictures Are Just Numbers How can a computer 'see' an image? It can't — but it can read numbers. Discover that every picture is really a grid of brightness values, setting up image AI. -
Project: Build a Guesser Put the whole machine-learning recipe together — load data, split it, train a model, check its accuracy, and make predictions on your own examples.