Evolutionary Algorithms (EAs) play a crucial role in the architectural configuration and
training of Artificial Deep Neural Networks (DNNs), a process known as neuroevolution …

Evolutionary algorithms are increasingly recognised as a viable computational approach for
the automated optimisation of deep neural networks (DNNs) within artificial intelligence. This …

Learning optimal policies in sparse rewards settings is difficult as the learning agent has
little to no feedback on the quality of its actions. In these situations, a good strategy is to …

Abstract Using Neuroevolution combined with Novelty Search to promote behavioural
diversity is capable of constructing high-performing ensembles for classification. However …

Bayesian optimization (BO) is a black-box search method particularly valued for its sample
efficiency. It is especially effective when evaluations are very costly, such as in …

Reinforcement Learning (RL) is the process of training agents to solve specific tasks, based
on measures of reward. Understanding the behavior of an agent in its environment can be …

Optimization plays an essential role in industrial design, but all too often it boils down to a
simple function to be minimized, such as cost or strength. More difficult considerations such …

Evolutionary computation (EC) methods belong to the state-of-the-art for solving optimization
problems with complex characteristics, such as no available analytical descriptions or no …

1 Zusammenfassung Das Projekt AErOmAt hatte zum Ziel, neue Methoden zu entwickeln,
um einen erheblichen Teil aerodynamischer Simulationen bei rechenaufwändigen …