
New Book: Interpretable Machine Learning
- Vincent Granville
- May 10, 2022
Subtitled “A Guide for Making Black Box Models Explainable”. Authored and self-published by Christoph Molnar, 2022 (319 pages). This is actually the second edition, the first one was published in 2019. According to Google Scholar, it was cited more than 2,500 times. So this is a popular book about a popular topic. General Comments The […]
Read More
New Book: Efficient Deep Learning
- Capri Granville
- May 8, 2022
Subtitled “Fast, smaller, and better models”. This book goes through algorithms and techniques used by researchers and engineers at Google Research, Facebook AI Research (FAIR), and other eminent AI labs to train and deploy their models on devices ranging from large server-side machines to tiny microcontrollers. The book presents a balance of fundamentals as well […]
Read More
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
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 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
Amazing 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 More
New 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 More
Why 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
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
Internship at MLtechniques: Code Translation
- Vincent Granville
- March 28, 2022
Interested in working 100% remotely for a fast paced digital company in the AI field? We offer off-the-beaten-path opportunities to machine learning experts, software engineers and beginners. Check out all our current openings, here. Internship: Code Translation Short-term project, under the guidance of Vincent Granville, with potential for more diversified work over a longer time […]
Read More
You must be logged in to post a comment.