
Little Known Secrets about Interpretable Machine Learning on Synthetic Data
- Vincent Granville
- May 7, 2022
This first article in a new series on synthetic data and explainable AI, focuses on making linear regression more meaningful and controllable. Includes synthetic data, advanced machine learning with Excel, combinatorial feature selection, parametric bootstrap, cross-validation, and alternatives to R-squared to measure model performance. The full technical article (PDF, 13 pages, with detailed explanations and […]
Read More
Computer Vision: Shape Classification via Explainable AI
- Vincent Granville
- April 20, 2022
Update: The technical report on this topic is now available in the Resources section, here. Look for the title “Classification of Shapes via Explainable AI” under Free Books and Articles. A central problem in computer vision is to compare shapes and assess how similar they are. This is used for instance in text recognition. Modern […]
Read More
Very Deep Neural Networks Explained in 40 Seconds
- Vincent Granville
- March 31, 2022
Very deep neural networks (VDNN) illustrated with data animation: a 40 second video, featuring supervised learning, layers, neurons, fuzzy classification, and convolution filters. It is said that a picture is worth a thousand words. Here instead, I use a video to illustrate the concept of very deep neural networks (VDNN). I use a supervised classification […]
Read More
New Book: Stochastic Processes and Simulations
- Vincent Granville
- March 22, 2022
Introduction This scratch course on stochastic processes covers significantly more material than usually found in traditional books or classes. The approach is original: I introduce a new yet intuitive type of random structure called perturbed lattice or Poisson-binomial process, as the gateway to all the stochastic processes. Such models have started to gain considerable momentum […]
Read More
You must be logged in to post a comment.