Peter Varhol

Writer

Peter Varhol is a well-known writer and speaker on software and technology topics, having authored dozens of articles and spoken at a number of industry conferences and webcasts. He has advanced degrees in computer science, applied mathematics, and psychology. Currently he has his own consulting company, Technology Strategy Research. His past roles include technology journalist, software product manager, software developer, and university professor.


When Your Network Fails to Converge

When Your Network Fails to Converge

Despite our best efforts at designing and training neural networks, sometimes a particular network simply won’t converge on a solution that is acceptable to the system requirements.  It could get close, but not meet requirements. ...

5 Guidelines for Building a Neural Network Architecture

5 Guidelines for Building a Neural Network Architecture

While power tools and libraries, such as Apache Spark and Intel’s Trusted Analytics Platform, make it possible to quickly design, implement, train, and test neural network applications, it is the algorithm (and the choices...

4 factors for testing machine learning applications

4 factors for testing machine learning applications

Machine learning systems seem a little bit like a math problem. Figure out the algorithm, pop in the data, and answers come out. But how do you know the answers are right? When you’re trying to predict what movies or books people...

Understanding Supervised Versus Unsupervised Networks

Understanding Supervised Versus Unsupervised Networks

Machine learning is really as simple as an algorithm that combs over any large data set and corresponding events, looking for patterns that allow it to predict the event in real data. That can be heart rhythms with heart attacks, mass...

An Intro to Genetic Algorithms

An Intro to Genetic Algorithms

Genetic algorithms are a form of machine learning that is focused on optimizing a particular output or outputs based on successive production of derived equations. The approach can be useful for optimizing a particular result when no...

Constructing Effective Neural Networks

Constructing Effective Neural Networks

Many commercial artificial intelligence and machine learning systems today use neural networks as their decision-making engine. Neural networks use layers of algebraic equations to process input data to produce accurate results in...

Load More