Overview and Scope
Generative Machine Learning has become a key field in machine learning and deep learning. In recent years, this field of research has proposed many deep generative models (DGMs) that range from a broad family of methods such as generative adversarial networks (GANs), variational autoencoders (VAEs), autoregressive (AR) models and stable diffusion models (SD). These models combine advanced deep neural networks with classical density estimation (either explicit or implicit) for mainly generating synthetic data samples. Although these methods have achieved state-of-the-art results in the generation of synthetic data of different types, such as images, speech, text, molecules, video, etc., Deep generative models are still difficult to train.
There are still open problems, such as the vanishing gradient and mode collapse in DGMs, which limit their performance. Although there are strategies to minimize the effect of those problems, they remain fundamentally unsolved. In recent years, evolutionary computation (EC) and related bio-inspired techniques (e.g. particle swarm optimization) and in the form of Evolutionary Machine Learning approaches have been successfully applied to mitigate the problems that arise when training DGMs, leveraging the quality of the results to impressive levels. Among other approaches, these new solutions include GAN, VAE, AR, and SD training methods or fine tuning optimization based on evolutionary and coevolutionary algorithms, the combination of deep neuroevolution with training approaches, and the evolutionary exploration of latent space.
This workshop aims to act as a medium for debate, exchange of knowledge and experience, and encourage collaboration for researchers focused on DGMs and the EC community. Bringing these two communities together will be essential for making significant advances in this research area. Thus, this workshop provides a critical forum for disseminating the experience on the topic of enhancing generative modelling with EC, presenting new and ongoing research in the field, and to attract new interest from our community.
More information at: EGML-EC 2023 (google.com)
- Lisbon, Portugal
- 15/07/2023 9:00 am
- Visit website