The most powerful computational model is the biological brain itself. In order to model a brain in a computer, the architecture and connectivity of neurons should be defined. However, none of the existing handcrafted computational models can reach its complexity. If we take a look in nature, the brain’s highly complicated structure results from the biological evolution of many millions of years. Inspired by this phenomenon, Neuroevolution (NE) is the field of artificial intelligence that aims to model the process of biological evolution inside computers. Towards this goal, NE uses Evolutionary Computation algorithms to optimize the parameters of Artificial Neural Networks (ANNs) such as the number of neurons and their connectivity. Through a number of studies my PhD thesis develops new neuroevolutionary algorithms that are able to evolve the architecture and the connectivity of ANNs simultaneously with identifying the relevant features of a task. The final algorithms are successfully applied on a real world application of detecting COVID-19 related lesions from patients at early stage.

"NeuroEvolution of Augmenting Topologies (NEAT) that evolves the topology and the connectivity weights of the ANNs, is one of the most influential algorithms in the field of NE."

My PhD performs different studies on NEAT extensions, namely FD-NEAT, FS-NEAT and HA-NEAT and proposes new extensions so that the resulting methods could require fewer generations, evolve smaller and less complex networks and scale on complex problems. Evolving smaller networks means that the networks have less parameters to optimize and the search space becomes smaller. This is a property of great importance when the amount of training data is limited. Clinical decision making and biomedical applications are examples of such tasks. In these cases a large number of features is often extracted for a small number of samples, resulting in the so called curse of dimensionality. Furthermore, feature selection is necessary to avoid overfitting.
After the publication of NEAT in 2002 many methods have appeared that extend its functionality in various ways. In this PhD, a systematic review is performed to identify and categorize the NEAT’s successors. The proposed clustering scheme can support researchers 1) understanding the current state of the art that will enable them 2) exploring new research directions or 3) benchmarking their proposed method to the state of the art, if they are interested in comparing, and 4) positioning themselves in the domain or 5) selecting a method that is most appropriate for their problem. In addition, different studies are conducted to achieve important intermediate stepping stones. The first set of investigations concern design choices in the initial topologies of two NEAT extensions, namely FD-NEAT and FS-NEAT. These include the introduction of a hidden layer in the initial topologies, the initialization of the topologies with a different connectivity setting and the employment of different activation functions in the output layer. Additionally, BS-HA-NEAT and BS-NEAT are proposed as new extensions of HA-NEAT and NEAT, that perform speciation in the behavioral rather than in the genotypic space. It is found that BS-HA-NEAT and BS-NEAT outperform HA-NEAT and NEAT solving previously unsolvable problems or improving the accuracy and reducing the complexity of the evolved networks. Furthermore, HA-FD-NEAT, extending both HA-NEAT and FD-NEAT is proposed. This is able to evolve the topology, the connectivity weights and the activation functions of ANNs while identifying the relevant features. HA-FD-NEAT outperforms HA-NEAT and performs as good as FD-NEAT. Also, BS-HA-FD-NEAT is proposed as an extension to HA-FD-NEAT by performing speciation in the behavioral space. BS-HA-FD-NEAT outperforms its ancestor by evolving significantly smaller networks. In overall, the resulting algorithm outperforms its ancestors, NEAT, FD-NEAT, and HA-NEAT achieving better accuracy, in fewer generations and evolving smaller and less complex networks. Finally, BS-HA-FD-NEAT is tested on a complex, real world application of reducing the false positives outputed from a detector of abnormal COVID-19 related findings from lung Computer Tomography (CT) images.

Research Interests 

Evolutionary Computation
Machine learning
Computer Aided Detection and Diagnosis Systems

Achievements (Honors & Awards) 
  • 2018: PhD grant for Strategic Basic Research (Renewal) by the Research Foundation Flanders (FWO)
  • 2017: Best challenge Resolution reward (3rd place) in the 1st Sigevo summer school
  • 2016: PhD grant for Strategic Basic Research by the Research Foundation Flanders (FWO)
  • 2015: Best poster (2nd place) by the National Belgian Committee on Biomedical Engineering at the 14th Belgian National Day on Biomedical Engineering
  • IEEE member
  • IEEE Computational Intelligence Society member