Books (By Me!)
Events (I Speak At!)
 2022 DevIntersection Conference
 2022 Predictive Analytics World
 2022 Black Hat Conference
 2022 Spring MLADS Conference
 2022 Money 20/20 Conference
 2022 DEFCON Conference
 2022 G2E Conference
 2022 Visual Studio Live Conference
 2021 National Homeland Security Conference
 2023 ICGRT Conference
 2023 CEC eSports Conference
 2021 Azure AI Conference
 2022 ISC West Conference

Recent Posts
Archives
Categories
Category Archives: Machine Learning
Why Neural Network Training Momentum Isn’t Used Very Often
During neural network training, it’s possible to use a momentum factor. Momentum is a technique designed to speed up training. But I hardly ever see momentum used. The main problem with momentum is that it adds another hyperparameter, the momentum … Continue reading
Posted in Machine Learning
1 Comment
Mahalanobis Distance Example Using Python
Suppose you have a source dataset of five items where each item is a person’s height, testscore, age: [64.0, 580.0, 29.0] [66.0, 570.0, 33.0] [68.0, 590.0, 37.0] [69.0, 660.0, 46.0] [73.0, 600.0, 55.0] And suppose you want the Mahalanobis distance … Continue reading
Posted in Machine Learning
Leave a comment
“Researchers Explore Machine Learning Hyperparameter Tuning Using Evolutionary Optimization” on the Pure AI Web Site
I contributed to an article titled “Researchers Explore Machine Learning Hyperparameter Tuning Using Evolutionary Optimization” in the November 2022 edition of the Pure AI web site. See https://pureai.com/articles/2022/11/01/evolutionaryoptimization.aspx. When data scientists create a machine learning prediction model, there are typically … Continue reading
Posted in Machine Learning
Leave a comment
Simple Numerical Optimization Using an Evolutionary Algorithm with C#
The goal of a numerical optimization problem is to find a vector of values that minimize some cost function. The most fundamental example is minimizing the Sphere Function f(x0, x1, .. xn) = x0^2 + x1^2 + .. + xn^2. … Continue reading
Posted in Machine Learning
Leave a comment
Traveling Salesman Problem Combinatorial Optimization Using an Evolutionary Algorithm with C#
A combinatorial optimization problem is one where the goal is to place items in a correct order. The classic example is the Traveling Salesman Problem (TSP). Suppose you have n = 20 cities that are numbered 0 to 19. There … Continue reading
Posted in Machine Learning
1 Comment
Why I Don’t Use Neural Network Early Stopping
I was chitchatting with a work colleague about early stopping. We were next to our workplace coffeemachine / engineerfuelingstation. I almost never use early stopping for neural network training. Briefly, 1.) it’s not really possible to determine when to stop, … Continue reading
Posted in Machine Learning
Leave a comment
Hyperparameter Tuning Using Evolutionary Optimization
All neural systems have hyperparameter values that must be determined by trial and error. Architecture hyperparameters include things like number of hidden layers, and hidden node activation. Training hyperparameters include things like learning rate and batch size. The system random … Continue reading
Posted in Machine Learning
Leave a comment
Hyperparameter Tuning Using Distributed Grid Descent
I was chitchatting with one of my work colleagues about an algorithm he created for hyperparameter tuning. The algorithm is called Distributed Grid Descent (DGD). Every neural prediction system has hyperparameters such as training learning rate, batch size, architecture number … Continue reading
Posted in Machine Learning
1 Comment
A Quick Look at TorchSharp
I ran across an interesting GitHub project called TorchSharp. Briefly, TorchSharp is PyTorch without the Python. Let me try to explain. PyTorch is 1.) a Python language wrapper over the libtorch.dll C++ library that implements lowlevel tensor functionality, and 2.) … Continue reading
Posted in Machine Learning
Leave a comment
Lasso Regression From Scratch Using Python
Lasso regression is just linear regression with L1 regularization. Let me explain. A linear regression problem is one where the goal is to predict a single numeric value from one or more numeric predictor values. For example, you might want … Continue reading
Posted in Machine Learning
2 Comments
You must be logged in to post a comment.