Good Data Means Fast Neural Network Training Times

The Pyrenn Levenberg-Marquardt training algorithm for Feed-Forward Neural Networks is extremely fast – 0.140 seconds for a Neural controller which must simultaneously balance an inverted pendulum, mounted on a cart, while moving the cart back to the origin – watch the short video below.

In the vast majority of the Neural Network applications that I’ve developed, the training time was a tiny fraction of my time spent on the project. The major time hit on these kinds of efforts is not training time – instead it is the time spent to develop quality and robust training and test data sets (thinking it through and careful analysis of the data – many times this is an iterative process). If this is done correctly, the resultant Neural Networks are built extremely quickly and yield high performance.


Published by Joys and Sorrows of Coding

Originally my degree was in Aerospace Engineering but I started coding in school and was hooked. In those days it was FORTRAN and reverse Polish notation on my hand-held HP 41-CV computer. Later I learned C, Pascal, Matlab, Java, C++, HTML and Python. Now I'm learning Android (Java) with Android Studio. The main IDEs that I use are NetBeans, IntelliJ IDEA, and Android Studio.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: