Upcoming Books and Articles on MLTechniques.com
- Vincent Granville
- April 25, 2022
The future of machine learning and artificial intelligence. Here I share my roadmap for the next 12 months. While I am also looking for external contributors and authors to add more variety, my focus — as far as my technical content is concerned — is to complete the following projects and publish the material on this platform. All my blog posts will be available to everyone.
Read MoreComputer 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 MoreAmazing Neural Network Video Demonstration
- Vincent Granville
- April 12, 2022
I recently posted an article featuring a very deep neural network in action (250 layers), see here. Each frame in the video represented one layer, with the signal propagating from one layer to the next. In the last layer, the whole space was classified, in the sense that any new observation was immediately assigned to […]
Read MoreNew Neural Network with 500 Billion Parameters
- Vincent Granville
- April 5, 2022
Google just published a research article about its Pathways Language Model (PaML), a neural network with 500 billion parameters. It is unclear to me how many layers and how many neurons (also called nodes) it can handle. A parameter in this context is a weight attached to a link between two connected neurons. So the […]
Read MoreWhy are Confidence Regions Elliptic? Simple Explanation
- Vincent Granville
- April 3, 2022
A 90% confidence region is a domain of minimum area, containing 90% of the mass of a distribution. By distribution, here I mean a bivariate probability distribution, though the concept is not specific to machine learning. The 90% is called the confidence level, and I denote it as γ. Confidence regions are a generalization of […]
Read More