About ETRO  |  News  |  Events  |  Vacancies  |  Contact  
Home Research Education Industry Publications About ETRO

Master theses

Current and past ideas and concepts for Master Theses.

A comparison of NEAT-based algorithms against machine learning methods on benchmark datasets


NeuroEvolution of Augmenting topologies is one of the most well known algorithms in evolutionary computation that enables the simultaneous learning of both the topology and the weights of Artificial Neural Networks. Feature Selective NEAT (FS-NEAT) and Feature De-selective NEAT (FD-NEAT) are two extensions of NEAT by means of performing additionally feature selection. Even though these algorithms have already shown their strength in reinforcement learning applications, lately there is a shift on supervised learning applications. However, the algorithms are only compared against other evolutionary methods and not against other machine learning algorithms.

Kind of work

In this master thesis the goal is to compare the performance of the NEAT based algorithms with other feature selection and classification algorithms on benchmark datasets. The objective is to create a robust and systematic comparison of the different machine learning methods. Towards this goal you would need to perform an in depth literature review to understand the different feature selection, classification and neuroevolutionary algorithms, to create artificial datasets as well as select the most appropriate public available datasets and implement the machine learning methods in Python.
Relevant Literature:

Framework of the Thesis

Number of Students



Prof. Dr. Bart Jansen

+32 (0)2 629 1034

more info


Ir. Evgenia Papavasileiou

+32 (0)2 629 1687

more info

- Contact person




- Contact person

- Thesis proposals

- ETRO Courses

- Contact person

- Spin-offs

- Know How

- Journals

- Conferences

- Books

- Vacancies

- News

- Events

- Press


ETRO Department

Tel: +32 2 629 29 30

©2019 • Vrije Universiteit Brussel • ETRO Dept. • Pleinlaan 2 • 1050 Brussels • Tel: +32 2 629 2930 (secretariat) • Fax: +32 2 629 2883 • WebmasterDisclaimer