Author Archives: jamesdmccaffrey

Recap of the 2021 ISC West Security Conference

Posted on July 26, 2021 by jamesdmccaffrey

I gave a short talk at 2021 ISC West Security Conference. The event was held July 19-21 in Las Vegas, Nevada. My talk was titled “AI and ML for Cyber Threat Prevention”. The ISC West event covers all aspects of … Continue reading →

Posted in Conferences | Leave a comment

Example of Kernel Density Estimation (KDE) Using SciPy

Posted on July 23, 2021 by jamesdmccaffrey

I was chit-chatting with a colleague a couple of days ago and the topic of kernel density estimation (KDE) came up. The first hurdle when trying to understand KDE is figuring out exactly what kind of problem the technique solves. … Continue reading →

Posted in Miscellaneous | Leave a comment

Dealing With PyTorch Library Versioning

Posted on July 22, 2021 by jamesdmccaffrey

It’s a major challenge to deal with the compatibility of the dozens of Python based libraries needed to work with the PyTorch neural network library. I was currently using PyTorch version 1.8 (for CPU) along with the Anaconda3-2020.02 distribution which … Continue reading →

Posted in PyTorch | Leave a comment

Zoltar 2021 NFL Football Predictions – Preparing Schedule Data

Posted on July 21, 2021 by jamesdmccaffrey

Zoltar is my NFL football prediction computer program. It uses a deep neural network and a form of reinforcement learning. I’ve been running Zoltar for several years and always enjoy the challenge — success or failure is unambiguous. It’s not … Continue reading →

Posted in Zoltar | Leave a comment

Researchers Use Machine Learning Techniques to Detect Compromised Network Accounts on the Pure AI

Posted on July 20, 2021 by jamesdmccaffrey

I contributed to an article titled “Researchers Use Machine Learning Techniques to Detect Compromised Network Accounts” on the Pure AI web site. See https://pureai.com/articles/2021/07/06/ml-detect.aspx. The article describes how researchers and engineers (including me) developed a successful system that detects compromised … Continue reading →

Posted in Machine Learning | Leave a comment

Differential Evolution Optimization Example Using Python

Posted on July 19, 2021 by jamesdmccaffrey

An Evolutionary Algorithm (EA) is one of many algorithms that are loosely based on the biological ideas of genetic crossover and mutation. Differential Evolution (DE) is a specific type of EA that has a bit of structure. I’m very familiar … Continue reading →

Posted in Machine Learning | Leave a comment

Computing PCA Using NumPy Without Scikit

Posted on July 16, 2021 by jamesdmccaffrey

Principal component analysis (PCA) is a classical statistics technique that can do data dimensionality reduction. This can be used to graph high dimensional data (if you reduce the dim to 2), or to clean data (by reconstructing the data from … Continue reading →

Posted in Machine Learning, PyTorch | 1 Comment

Particle Swarm Optimization Variants

Posted on July 15, 2021 by jamesdmccaffrey

Particle swarm optimization (PSO) is a meta-heuristic that can be used to construct a specific algorithm to find the minimum of an error function. In theory, PSO could improve neural network training because PSO does not use Calculus gradients like … Continue reading →

Posted in Machine Learning | Leave a comment

Sentiment Analysis Using a PyTorch EmbeddingBag Layer in Visual Studio Magazine

Posted on July 14, 2021 by jamesdmccaffrey

I wrote an article titled “Sentiment Analysis Using a PyTorch EmbeddingBag Layer” in the July 2021 edition of the online Microsoft Visual Studio Magazine. See https://visualstudiomagazine.com/articles/2021/07/06/sentiment-analysis.aspx. Natural language processing (NLP) problems are very difficult. A common type of NLP problem … Continue reading →

Posted in Machine Learning, PyTorch | Leave a comment

Jensen-Shannon Distance Example

Posted on July 13, 2021 by jamesdmccaffrey

The Jensen-Shannon distance measures the difference between two probability distributions. For example, suppose P = [0.36, 0.48, 0.16] and Q = [0.30, 0.50, 0.20]. The Jenson-Shannon distance between the two probability distributions is 0.0508. If two distributions are the same, … Continue reading →

Posted in Miscellaneous | Leave a comment