This is the third lesson in our Computer Science Education series. In How a Computer Works students learned that everything inside a machine is binary. In How AI Learns they saw that clever behaviour can come from very simple steps…
How the Internet Works, An Animated Lesson for High School Read More »
A fraud team has a transaction graph with a few million accounts. Almost all of them are ordinary. A few hundred belong to a ring that launders money through layered transfers. When a graph neural network classifies those accounts, each…
CL3E-GNN and the Imbalanced Node Classification Problem Read More »
A player sees a little boat miss a narrow harbor entrance. The mistake is obvious, the goal is understandable, and the player thinks they could do better. A moment later, they are steering. No explanation of the game engine was…
Meta Horizon Create and the Rise of Social AI Games Read More »
An interactive lesson on how AI learns. Train a neuron, watch gradient descent and build a next word predictor, with a quiz and Python code.
How AI Learns: An Animated Guide to Neural Networks Read More »
You ask an AI tool to build a tiny delivery game. A character moves, parcels appear, and a score climbs. Then you press restart and discover that the previous score survived. The first generation looked convincing. The second session exposed…
Google Playground and Unity Spark for Game Developers Read More »
You are fitting a tensor decomposition. Every factor update solves a manageable problem, the reconstruction error keeps falling, and the run eventually seems to settle. Then another initialization takes much longer. Adding a small quadratic penalty helps, until you impose…
Block Riemannian Optimization and RBMM Guarantees Read More »
This article is written for two readers at once. The first is a computer teacher preparing a unit on computer fundamentals for grades nine to twelve, whether that follows a matriculation syllabus, an O Level course, or a general introduction…
How a Computer Works, An Animated Lesson for High School Read More »
An analyst has five thousand unlabelled records and one colleague who actually understands them. The colleague will not label five thousand rows. They will, if asked politely, look at two records at a time and say whether they belong together.…
FALCON Asks Better Clustering Questions With MMD Read More »
It is the middle of a night shift in an intensive care unit. One patient has a full set of overnight labs and a running stream of vital signs. The patient in the next bed has demographics and diagnosis codes…
ETF-UML Fuses Incomplete ICU Data Without Joint Training Read More »
A volunteer lies in a scanner at one of the Human Connectome Project sites. A screen flashes a cue, and for the next ten seconds or so they tap fingers, listen to a story, or hold a picture of a…
ASFFNet Decodes Brain States From Shorter fMRI Windows Read More »