Ecological Analogy for Generative Adversarial Networks and Diversity Control

Abstract

Generative adversarial networks are popular deep neural networks for generative modeling in the field of artificial intelligence. In the generative modeling, we want to output a sample with some random numbers as an input. We train the artificial neural network with a training data set for the purpose. The network is known with astonishingly fruitful demonstrations, but we know the difficulty in the training because of the complex training dynamics. Here, we introduce an ecological analogy for the training dynamics. With the simple ecological model, we can understand the dynamics. Furthermore, a controller for the training can be designed based on the understanding. We then demonstrate how the network and the controller work with an ideal case, MNIST.