Category Archives: Machine Learning

My First Impressions Of The fast.ai Library Were Not Good

The fast.ai library is a set of wrapper functions over the PyTorch code library. See ww.fast.ai. The idea is that PyTorch operates at a low level of abstraction and is quite difficult to learn and use. The fast.ai library provides … Continue reading

Posted in Machine Learning | Leave a comment

Binary Classification with Logistic Regression Using ML.NET

I’ve been poking around the ML.NET code library. ML.NET is a C# library that can do classical machine learning (but not neural systems). ML.NET is a very large library and just like most things, it can only be learned by … Continue reading

Posted in Machine Learning | Leave a comment

Why Machine Learning One-Versus-All is Not a Good Technique

In machine learning, using the one-versus-all technique is almost never a good idea. One-versus-all (OvA) is also called one-versus-rest (OvR), and several other similar terms. A binary classification problem is one where the goal is to predict something that can … Continue reading

Posted in Machine Learning | 2 Comments

Feature Engineering and Machine Learning

Suppose you want to predict a person’s annual income based on their number years of experience, age, number years education, and so on. In classical statistics it’s common to spend a lot of time on feature engineering — deciding which … Continue reading

Posted in Machine Learning | 1 Comment

Trying to Understand the Microsoft Machine Learning Ecosystem

There are several different kinds of machine learning systems (libraries, platforms, tools, etc.) in the Microsoft technology ecosystem. All of these systems were originally developed independently, but over time each system evolved and there’s been an effort to unify most … Continue reading

Posted in Machine Learning | Leave a comment

How to Do Neural Network Glorot Initialization Using Python

I wrote an article titled “How to Do Neural Network Glorot Initialization Using Python” in the August 2019 issue of Visual Studio Magazine. See https://visualstudiomagazine.1105cms01.com/articles/2019/09/05/neural-network-glorot.aspx. In the article I explain what neural network Glorot initialization is and why it has … Continue reading

Posted in Machine Learning | Leave a comment

Machine Learning and Counterfactuals and Interpretability

A counterfactual is a statement or fact like, “If your income had been $10,000 more and your credit rating had been 50 points higher, your loan application would have been approved instead of rejected.” Suppose you work for a bank. … Continue reading

Posted in Machine Learning