Books (By Me!)
Events (I Speak At!)
2022 Predictive Analytics World
2022 DevIntersection Conference
2022 Visual Studio Live Conference
2021 Fall MLADS Conference
2021 TDWI Conference
2021 DEFCON Conference
2021 G2E Conference
2021 National Homeland Security Conference
2021 Azure AI Conference
2021 ISC West Conference
2021 Money 20/20 Conference
2021 ConnectIT Conference
Author Archives: jamesdmccaffrey
NFL 2021 Week 18 Predictions – Zoltar Likes the Vegas Underdogs
Zoltar is my NFL football prediction computer program. It uses custom reinforcement learning and a neural network. Here are Zoltar’s predictions for week #18 of the 2021 season. It usually takes Zoltar about four weeks to hit his stride and … Continue reading
Posted in Zoltar
Leave a comment
Why Proving Computer Program Correctness Isn’t Usually Practical
I think I first learned about mathematical proofs in my high school geometry class. We learned how to prove that two triangles are congruent using the side-angle-side theorem (“If two sides and the included angle of one triangle . . … Continue reading
Posted in Miscellaneous
Leave a comment
PyTorch Training Checkpoint Exact Recovery Reproducibility
About a year ago I spent many days figuring out how to save a PyTorch training checkpoint in such a way that it’s possible to load the saved information and resume training in a way that’s exactly like the original … Continue reading
Posted in PyTorch
Leave a comment
What Are Progressive Neural Networks for Transfer Learning?
Deep neural networks have made incredible progress in tabular data classification and regression, natural language processing, and image recognition. But one of the weaknesses of DNNs is that they are very problem-specific. A DNN trained to play chess doesn’t do … Continue reading
Posted in Machine Learning
Leave a comment
Matrix Determinant from Scratch Using Python
A few days ago I was exploring the ideas behind implementing matrix inversion from scratch using Python. There are dozens of matrix inversion algorithms but the one I usually use involves decomposing the source matrix into two other matrices. And … Continue reading
Posted in Machine Learning
Leave a comment
NFL 2021 Week 17 Predictions – Zoltar Likes the Favorite Cowboys Over the Cardinals
Zoltar is my NFL football prediction computer program. It uses custom reinforcement learning and a neural network. Here are Zoltar’s predictions for week #17 of the 2021 season. It usually takes Zoltar about four weeks to hit his stride and … Continue reading
Posted in Zoltar
Leave a comment
Researchers Explore Quantum-Inspired Optimization on the Pure AI Web Site
I contributed to an article titled “Researchers Explore Quantum-Inspired Optimization” in the December 2021 edition of the Pure AI web site. See https://pureai.com/articles/2021/12/01/quantum-inspired-optimization.aspx. Quantum-inspired optimization starts with a standard algorithm, such as particle swarm optimization or simulated annealing, and modifies … Continue reading
Posted in Machine Learning
Leave a comment
The Gamma Function Implemented using C#
The mathematical Gamma function appears in many areas of classical statistics and numerical programming. There are many ways to think about what the Gamma function is. I usually think about Gamma(n) as a function that equals Factorial(n-1) where n can … Continue reading
Posted in Miscellaneous
Leave a comment
My Top Ten Favorite Christmas Movies
There are a lot of movies that have some sort of Christmas theme, and there are a lot of top 10 lists of such movies. Here is my list. I don’t include animated films such as “A Charlie Brown Christmas”. … Continue reading
Posted in Top Ten
Leave a comment
Matrix Decomposition Using Python
One of the fundamental algorithms in machine learning and numerical programming is matrix decomposition. The idea is to break a source matrix M into two matrices A and B so that A * B = M. Matrix decomposition doesn’t have … Continue reading
Posted in Machine Learning
Leave a comment
.NET Test Automation Recipes
Software Testing
SciPy Programming Succinctly
Keras Succinctly
R Programming
James D. McCaffrey 
You must be logged in to post a comment.