COEGAN: Evaluating the Coevolution Effect in Generative Adversarial Networks

12/12/2019
by   Victor Costa, et al.
0

Generative adversarial networks (GAN) present state-of-the-art results in the generation of samples following the distribution of the input dataset. However, GANs are difficult to train, and several aspects of the model should be previously designed by hand. Neuroevolution is a well-known technique used to provide the automatic design of network architectures which was recently expanded to deep neural networks. COEGAN is a model that uses neuroevolution and coevolution in the GAN training algorithm to provide a more stable training method and the automatic design of neural network architectures. COEGAN makes use of the adversarial aspect of the GAN components to implement coevolutionary strategies in the training algorithm. Our proposal was evaluated in the Fashion-MNIST and MNIST dataset. We compare our results with a baseline based on DCGAN and also with results from a random search algorithm. We show that our method is able to discover efficient architectures in the Fashion-MNIST and MNIST datasets. The results also suggest that COEGAN can be used as a training algorithm for GANs to avoid common issues, such as the mode collapse problem.

READ FULL TEXT

page 6

page 8

research
12/12/2019

Coevolution of Generative Adversarial Networks

Generative adversarial networks (GAN) became a hot topic, presenting imp...
research
06/28/2018

Training Discriminative Models to Evaluate Generative Ones

Generative models are known to be difficult to assess. Recent works, esp...
research
05/24/2018

Autonomously and Simultaneously Refining Deep Neural Network Parameters by Generative Adversarial Networks

The choice of parameters, and the design of the network architecture are...
research
06/11/2018

Generative Adversarial Network Architectures For Image Synthesis Using Capsule Networks

In this paper, we propose Generative Adversarial Network (GAN) architect...
research
05/19/2020

Regularization Methods for Generative Adversarial Networks: An Overview of Recent Studies

Despite its short history, Generative Adversarial Network (GAN) has been...
research
10/10/2018

Training Generative Adversarial Networks with Binary Neurons by End-to-end Backpropagation

We propose the BinaryGAN, a novel generative adversarial network (GAN) t...
research
09/27/2017

Generative Adversarial Networks with Inverse Transformation Unit

In this paper we introduce a new structure to Generative Adversarial Net...

Please sign up or login with your details

Forgot password? Click here to reset