How can I apply multithreading to the backpropagation neural network training?

Question

For my university project, I am creating a neural network that can classify the likelihood that a credit card transaction is fraudulent or not. I am training with backpropagation. I am writing this in Java. I would like to apply for multithreading, because my computer is a quad-core i7. It bugs me to spend hours training and sees most of my cores idle.

But how would I apply multithreading to backpropagation? Backprop works by adjusting the errors backward through the network. One layer must be done before the other can continue. Is there any way that I can modify my program to do multicore backdrop?

Answer 1

There are various techniques for implementing multithreading in backpropagation.

Generally, supervised neural networks are trained with resilient propagation (RPROP) or backpropagation. RPROP is considered the modern of the two and is almost always the preferred solution. You can enhance the Encog Artificial Intelligence Framework to make use of multithreading to provide fast training on multicore machines.  

You can refer the following link for better understanding:

https://www.heatonresearch.com/encog/mprop/compare.html