Category Archives: Applied Math

A Surprising Pitfall of Human Judgement and How to Correct It

Introduction Algorithms based on machine learning, deep learning, and AI are in the news these days. Evaluating the quality of these algorithms is usually done using human judgment. For example, if an algorithm claims to detect whether an image contains a pet, the claim can be checked by selecting a sample of images, using human
Continue Reading »

Statistical Anomaly Detection

Complex systems can fail in many ways and I find it useful to divide failures into two classes. The first consists of failures that can be anticipated (e.g. disk failures), will happen again, and can be directly checked for. The second class is failures that are unexpected.  This post is about that second class. The tool for unexpected
Continue Reading »