1 code implementation • 6 Jul 2022 • Victor Costa, Nuno Lourenço, João Correia, Penousal Machado
In this work, we follow a different direction by proposing the use of Covariance Matrix Adaptation Evolution Strategy to explore the latent space of Generative Adversarial Networks.
no code implementations • 31 Jan 2021 • Victor Costa, Nuno Lourenço, João Correia, Penousal Machado
Evolutionary algorithms, such as COEGAN, were recently proposed as a solution to improve the GAN training, overcoming common problems that affect the model, such as vanishing gradient and mode collapse.
1 code implementation • 13 Jul 2020 • Victor Costa, Nuno Lourenço, João Correia, Penousal Machado
We compare our proposal with the original COEGAN model and with an alternative version using a global competition approach.
no code implementations • 9 Apr 2020 • Victor Costa, Nuno Lourenço, João Correia, Penousal Machado
Recent works proposed the use of evolutionary algorithms on GAN training, aiming to solve these challenges and to provide an automatic way to find good models.
1 code implementation • 12 Dec 2019 • Victor Costa, Nuno Lourenço, João Correia, Penousal Machado
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.
no code implementations • 12 Dec 2019 • Victor Costa, Nuno Lourenço, Penousal Machado
Therefore, this project proposes COEGAN, a model that combines neuroevolution and coevolution in the coordination of the GAN training algorithm.