Historical averaging is an approach that takes the average of the parameters in the past and adds this to the respective cost functions of the generator and the discriminator network. It was proposed by Ian Goodfellow and others in a paper mentioned previously, Improved Techniques for Training GANs.
The historical average can be denoted as follows:
In the preceding equation, 
is the value of parameters at a particular time, i. This approach can improve the training stability of GANs too.
Get Generative Adversarial Networks Projects now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
Get Mark Richards’s Software Architecture Patterns ebook to better understand how to design components—and how they should interact.
Dive in for free with a 10-day trial of the O’Reilly learning platform—then explore all the other resources our members count on to build skills and solve problems every day.
Start your free trial Become a member now