Projects
A collection of research projects, software applications, and computational experiments.
NLP Bias
Bias is an important topic in NLP language models. With their great applicability and increasing influence in our lives the potential influence and danger of bias is great. This paper inspects the validity and reliability of the CrowS-Pairs metric on gender bias by fine-tuning a GPT model on different stereotype ratio of the BUG dataset.
NLP Probing
Probing neural language models to understand what linguistic knowledge they encode.
NLP - Hallucinations
While natural language generation has seen significant improvements, hallucinations remain a critical issue, producing irrelevant or factually incorrect information. This project develops an ensemble of metrics to evaluate factual correctness in generated text. Our findings demonstrate that fine-tuning effectively mitigates hallucinations, whereas prompt engineering shows limited effectiveness.
Bachelor Thesis - Damen
Research project conducted at Damen Shipyards on computational methods.
Master Thesis - Predictive Coding @ SILS
Investigating predictive coding mechanisms in neural networks at the Systems, Information, Learning & Society Lab.
AI4Med Ribfrac
Detection of rib fractures in CT scans with UNet3+.
ML Reproducibility - LASSI
Reproducibility study of Latent Space Smoothing for Individually Fair Representation (LASSI). Verifying claims about incorporating individual fairness into deep learning models.
Game of Life in C++
Conway's Game of Life implementation with high-performance C++ optimization.
2D lattice-Boltzmann particle flow
A simple lattice-Boltzmann implementation for 2D flow simulations with particle tracking.
Trading Bot
Automated trading system using machine learning and algorithmic strategies.
Black Hole Visualization
Interactive WebGL visualization of a black hole with gravitational lensing effects and accretion disk rendering.
