Performance comparison of different federated learning aggregation algorithms: How does the performance of different federated learning aggregation algorithms compare to each other?

Federated learning enables the construction of machine learning models, while adhering to privacy constraints and without sharing data between different devices. It is achieved by creating a machine learning model on each device that contains data, and then combining these models through an aggregation algorithm without sharing the data....

Evaluating Feature Attribution Methods: an Usecase on a Neural Fact-checking Model

In today's society, claims are everywhere, in the online and offline world. Fact-checking models can check these claims and predict if a claim is true or false, but how can these models be checked? Post-hoc XAI feature attribution methods can be used for this. These methods give scores indicating the influence of the individual tokens on the...

Model-Agnostic XAI Models: Benefits, Limitations and Research Directions

The ever increasing presence of Machine Learning (ML) algorithms and Artificial Intelligence (AI) agents in safety-critical and sensitive fields over the past few years has spurred massive amounts of research in Explainable Artificial Intelligence (XAI) techniques (models). This new frontier of AI research aims to resolve some of the fundamental...

Posits als vervanging van floating-points: Een vergelijking van Unum Type III Posits met IEEE 754 Floating Points met Mathematica en Python

In dit verslag worden de resultaten van literatuuronderzoek naar de voor- en<br/>nadelen van floats en posits gepresenteerd. Naar aanleiding van de resultaten is de hypothese opgesteld dat posits een goede "drop-in replacement" zouden zijn voor floats vanwege het grotere bereik, de afwezigheid van overflow en underflow en omdat ze enkel één NaN...