Medical image processing can lack images for diagnosis. Generative Adversarial Networks
(GANs) provide a method to train generative models for data augmentation. Synthesized …

Labeling images for classification can be expensive. Semi-Supervised Learning (SSL)
Generative Adversarial Network (GAN) methods train good classifiers with a few labeled …

Competitive co-evolutionary algorithms (CoEAs) do not rely solely on an external function to
assign fitness values to sampled solutions. Instead, they use the aggregation of outcomes …

In the last decade, generative models have seen widespread use for their ability to generate
diverse artefacts in an increasingly simple way. Historically, the use of evolutionary …

It can be expensive to label images for classification. Good classifiers or high-quality images
can be trained on unlabeled data with Generative Adversarial Network (GAN) methods. We …

Abstract Adversarial Evolutionary Learning (AEL) is concerned with competing adversaries
that are adapting over time. This competition can be defined as a minimization …

Machine Learning models often require a large amount of data in order to be successful.
This is troublesome in domains where collecting real-world data is difficult and/or expensive …

Training autoencoders is non-trivial. Convergence to the identity function or overfitting are
common pitfalls. Population based algorithms like coevolutionary algorithms can provide …

Competitive coevolutionary algorithms (CoEAs) often encounter so-called coevolutionary
pathologies particularly cycling behavior, which becomes more pronounced for games …

We explore the use of Artificial Neural Network (ANN)-guided Genetic Programming (GP) to
generate images that the guiding network classifies as belonging to a specific class. The …