"How Much Data is Enough?" Learning Curves for Machine Learning

Supervisors: Jesse Krijthe, Tom Viering

The influence of the dimensionality on the parameters of the learning curve model

By Andrei Mereuta

A Comparative Analysis of Learning Curve Models and their Applicability in Different Scenarios

By Anna Kalandadze

Non-Monotonicity in Empirical Learning Curves

By Codrin Socol

Empirical Investigation of Learning Curves: Assessing Convexity Characteristics

By Kristián Gogora

Investigating alternatives to the Levenberg-Marquardt algorithm for learning curve extrapolation

By Lucian Negru

A Test Suite for Quantum Network Applications

Supervisors: Stephanie Wehner, Ravi Vattekkat

A test suite for quantum network applications: Quantifying an application`s ability to benchmark a quantum network

By Arnav Chopra

A Test Suite for Quantum Networks: Assessing an application`s effectiveness as a benchmark for quantum networks

By Casper Dekeling

Laying the foundation for building a Quantum Networking Benchmark suite using Quantum Network Applications

By Thomas Maliappis

A Test Suite for Quantum Network Applications: Evaluation of the Distributed CNOT Application in its Ability to Benchmark Quantum Networks

By Wout van Loevezijn

A Virtual Reality Game to Explore Hyperbolic Geometry

Supervisors: Martin Skrodzki, Rafael Bidarra

Mapping hyperbolic space for the virtual reality game "Holonomy"

By Ate-Jan de Vries

Exploring the Impact of a Procedurally Generated Environment on Immersion in Virtual Hyperbolic Space

By Joris Rijsdijk

Shortest Path algorithms for the traversal of an Order-5 square tiling from within a confined space

By Ravi Snellenberg

Rendering Non-Euclidean Space in Virtual Reality Using Portals

By Riley Slotboom

Mini-map positioning for Virtual Reality environments in hyperbolic space

By Scott Jochems

A computer-checked library of category theory

Supervisors: Benedikt Ahrens, Lucas Escot

Formally verifying currying via the product-exponential adjunction

By Ciprian Stanciu

The monad and examples from Haskell

By Csanád Farkas

Universal Properties of Category Theory in Functional Programming

By Markus Orav

Functors and F-Coalgebras

By Pedro Brandao de Araujo

Defining functors and their algebras

By Rado Todorov

AI in Coding: How can code generation models support students developing computational thinking skills?

Supervisors: Fenia Aivaloglou, Xiaoling Zhang

How can large language models and prompt engineering be leveraged in Computer Science education?

By Alexandra-Ioana Neagu

Use of AI-driven code generation models in teaching and learning programming: a systematic literature review

By Doga Cambaz

How well does ChatGPT perform on course assignments from the TU Delft Computer science and engineering Bachelor?

By Mike Segers

In-IDE code generation models - a literature review

By Rebeca Varzaru

The use of code generation models in programming support activities

By Rick Mulder

Advances and Challenges in Traffic Forecasting with Deep Learning Methods

Supervisors: Elena Congeduti

Long term predictions for traffic forecasting, how does the accuracy degrade with time

By Bas Verlooy

Effects of weather data on traffic flow predictions using an LSTM deep learning model

By Nikola Nachev

Deep learning approaches to short term traffic forecasting. Capturing the spatial temporal relation in historic traffic data

By Thomas Kuiper

Assessing Methods for Handling Missing Data Using an LSTM Deep Learning Model in Traffic Forecasting

By Wouter Buthker

Comparative Analysis of LSTM, ARIMA, and Facebook`s Prophet for Traffic Forecasting

By Ziyar Uzel

Agent failure and trust repair in human-agent teams

Supervisors: Myrthe Tielman, Ruben Verhagen

The Influence of Interdependence on Trust Repair and Fluency

By Alexandra Maria Marcu

The Influence of Interdependence on Trust Repair in Human-Agent Teams

By Cherin Kim

Agent Failure, Trust Repair, and Fluency in Human-AI Teams

By Kanta Tanahashi

Agent Failure and Trust Repair in Human-Agent Teams

By Tauras Narbutas

Annotation Practices in Societally Impactful Machine Learning Applications: What are these automated systems actually trained on?

Supervisors: Cynthia Liem, Andrew Demetriou

Investigating Data Collection and Reporting Practices of Human Annotations in Societally ...

By Ahmed Ibrahim

Annotation Practices in Machine Learning Research On Depression

By Aleksandra Andrasz

Annotation Practices in Societally Impactful Machine Learning Applications: What are the recommender...

By Andra-Georgiana Sav

A Quest Through Interconnected Datasets: From International conference on International Conference ...

By Doğa Taşcılar

Annotation Practices in Affective Computing

By Suzanne Backer

Assessing ML Algorithm Robustness to Sample Selection Bias

Supervisors: Joana de Pinho Gonçalves, Yasin Tepeli

Evaluating the Effectiveness of Importance Weighting Techniques in Mitigating Sample Selection Bias

By Andrei Tociu

Generalizability of Deep Domain Adaptation in case of Sample Selection Bias

By Emiel Witting

The effectiveness of subspace mapping techniques adapted to unlabeled samples from a global domain in mitigating sample selection bias

By Timo van Hoorn

Evaluating the effectiveness of semi-supervised learning techniques

By Viraj Biharie

How effective are minimax methods in mitigating sample selection bias?

By Zeeshan Khan

Automatic feature discovery to improve Machine Learning performance

Supervisors: Asterios Katsifodimos, Andra Ionescu

Automatic Feature Discovery: A comparative study between filter and wrapper feature selection techniques

By Andrei Manastireanu

Encoding Methods for Categorical Data: A Comparative Analysis for Linear Models, Decision Trees, and Support Vector Machines

By Andrei Udila

A comparative study for using PCA, LDA, GDA, and Lasso for dimensionality reduction before classification algorithms

By Duyemo Anceaux

Data-Driven Empirical Analysis of Correlation-Based Feature Selection Techniques

By Florena Buse

Filtering Knowledge: A Comparative Analysis of Information-Theoretical-Based Feature Selection Methods

By Kiril Vasilev

Binary bit clustering algorithm

Supervisors: Marcel Reinders, Gerard Bouland

Similarity metrics for binary cell clustering: How close can we get to state-of-the-art?

By Bartosz Golik

Binarized single cell RNA sequencing data clustering: The impact of binarized scRNA-seq data on clustering through community detection algorithms

By Jurrien Theunisz

Evaluating runtime in Binary clustering of Single-cell RNA Sequencing data

By Milan de Koning

Memory usage analysis of binary clustering algorithm

By Pavel Verigo

Building Type Checkers Using Scope Graphs

Supervisors: Casper Bach Poulsen, Aron Zwaan

Building type checkers using scope graphs for a language with type classes

By Andreea Mocanu

Type checker for a language with a substructural type system using scope graphs

By Jan Knapen

Phased Type Checker For Java

By Omar Thabet

Type-Checking Modules and Imports using Scope Graphs

By Paul Hübner

Building Type Checkers Using Scope Graphs: Scope Graph-Based Type Checking for a Scala Subset

By Radu-Gabriel Mihălăchiuță

Combinatorial Optimisation for Scheduling (NP-Hard Algorithms)

Supervisors: Emir Demirović, Konstantin Sidorov, Maarten Flippo

Combinatorial optimization for JSOCMSR problem by using a SAT solver augmented with a domain-specific heuristic

By Artjom Pugatšov

Integration of variable selection heuristics into a MaxSAT solver for solving the MRCPSP

By Denis Tsvetkov

How can heuristics make SAT faster for the Preemptive Resource-Constrained project scheduling problem with set up time?

By George Hellouin de Menibus

Combining SAT solvers with heuristic ideas for solving RCPSP with logical constraints

By Iarina Tudor

Augmenting VSIDS heuristic for the RCPSP/t by initializing activity values using domain-specific information

By Tijs Lenssen

Combinatorial Optimization for Decision Trees (NP-Hard Algorithms)

Supervisors: Emir Demirović, Koos van der Linden

Optimal Robust Decision Trees: A dynamic programming approach

By Benedict Bien

Individually fair optimal decision trees, using a dynamic programming approach

By Chrysanthos Kindynis

Optimal decision trees for the Algorithm Selection Problem: A dynamic programming approach

By Giulio Segalini

Optimal Regression Trees via Dynamic Programming: Optimization techniques for learning Regression Trees

By Mim van den Bos

SurTree: constructing optimal survival trees with MurTree

By Tim Huisman

Comics Illustration Synthesizer using Deep Generative Models

Supervisors: Lydia Chen, Zilong Zhao

Clustering Faces of Comic Characters: An Experimental Investigation

By Artun Boz

Controlloing Poisson Flow Generative Models

By Ioannis Georgiades

Does text matter?: Extending CLIP with OCR and NLP for image classification and retrieval

By Jordan Sassoon

Pipeline construction for the automated text retrieval, editing, and deletion in comic illustrations

By Jordin van Setten

Comics Illustration Synthesizer using the Stable Diffusion Model: Fine-tuning for text-to-image Dilbert Comics Generation

By Mahmoud Elaref

Comparing planners for rail planning

Supervisors: Sabastijan Dumancic, Issa Hanou

Mixed-direction train shunting with numerical planning

By Ákos Sárkány

Utilizing General Planners to Solve the Train Unit Shunting Problem Extended with Servicing

By Bozhidar Andonov

Dealing with conflicting trains

By Mees Gribnau

Optimizing the PDDL domain of TUSP to improve planner performance

By Simba Chiu

Comparing planners for rail planning in PDDL

By Tim Tian

Computer-checked Proofs in Homotopy Type Theory

Supervisors: Kobe Wullaert, Benedikt Ahrens

Calculating the Fundamental Group of the Circle in Homotopy Type Theory: Formalized in the Coq Unimath library

By Jeroen van Heiningen

Kuratowski Finite Sets in UniMath library

By Luuk van de Laar

Formalising the Symmetry Book

By Pallabi Sree Sarker

Isomorphism is equality

By Tiago Greeve

Concurrency Testing of Distributed Consensus Algorithms

Supervisors: Burcu Kulahcioglu Ozkan, Ege Berkay Gulcan

Statistical Bug Isolation for Consensus Systems

By Levin N. Winter

Concurrency Testing of PBFT: How do different exploration strategies perform for detecting concurrency bugs in PBFT?

By Martin Petrov

Concurrency Testing of the HotStuff Distributed Consensus Algorithm

By Wenkai Li

Cooperative AI for Overcooked!

Supervisors: Frans Oliehoek, Robert Loftin

Scripted AI for Overcooked

By Cosmin Anton

Improvements in Imitation Learning for Overcooked

By Duuk Niemantsverdriet

Multi-Agent RL with Population-Based Training

By Ivan Nestorov

Getting AI to Cooperate: Sharing a Critic in a Video Game

By Jelle Groenendijk

Cooperative AI and Planning Algorithms in Overcooked

By Jonte Herben

Correct-by-construction refactoring of functional code

Supervisors: Jesper Cockx, Luka Miljak

Proving correctness of refactoring tuples to records: A correct-by-construction approach on a Haskell-like language

By Jeroen Bastenhof

Maybe a List would be better?: Correct by construction Maybe to List refactorings in a Haskell-like language

By José Carlos Padilla Cancio

Refactoring with confidence: Creating and proving the correctness of a refactoring to add arguments to a function in a functional language

By Kalle Struik

Formally proving the correctness of the (un)currying refactoring: Using Agda with a simple Haskell-like programming language

By Michał Jóźwik

Don’t bind yourself to do notation!: Using Agda to Prove Correctness of Refactorings on Monads

By Timen Zandbergen

Creation of Gang Territories and other Patterns

Supervisors: Martin Skrodzki, Alethea Barbaro

Territory patterns created by random walker agents in three dimensions

By Abel de Bruijn

Effects of City Layout in Gang Territorial Formations

By Damla Ortac

Implementation and Evaluation of an Order Parameter for the Reaction-Diffusion Model in a Cellular Automaton

By Daniel Puente Barajas

A cellular automaton for modelling territories

By Maarten van Bijsterveldt

Multi Species Turing Patterns in Three Dimensions

By Rens Dur

Cultural Differences and Similarities in Perceptions of Artificial Social Agents (ASAs)

Supervisors: Willem-Paul Brinkman, Nele Albers

Differences and similarities in perceptions of interactions with Artificial Social Agents between German and English speakers

By Boleslav Khodakov

Cultural Differences and Similarities in Perceptions of Artificial Social Agents Between German and Chinese Speakers

By Emma Bokel

Perceptions of Artificial Social Agents

By Johan Hensman

Deep learning-based Gaze Estimation

Supervisors: Guohao Lan, Lingyu Du

Adversarial Attack and Training on Deep Learning-based Gaze estimation

By Clio Feng

Data augmentation for deep learning-based gaze estimation

By Jorn Dijk

Exploring The Influence of Facial Features Beyond Eyes on Gaze Estimation

By Tan Nguyen

Channel Selection for Faster Deep Learning-based Gaze Estimation in the Frequency

By Thijs Penning

Backdoor Attack On Gaze Estimation

By Yuji Reda

Descriptive CI Metrics

Supervisors: Sebastian Proksch, Shujun Huang

GitHub Mining: The Implementation of Continuous Integration Pipelines

By Bram de Vries

Discovering the metrics for assessing a project`s maturity: An analysis of key indicators of maturity

By Kendra Sartori

Discovering the topics of Continuous Integration projects on GitHub

By Lukas Ostrovskis

Github Mining: Discover the Descriptive Metrics of the Context in Continuous Integration (CI) Project

By Patrick Hibbs

Exploring Descriptive Metrics of Build Performance: A Study of GitHub Actions in Continuous Integration Projects

By Radu Stefan Constantinescu

Detection of critical infrastructure devices on the public Internet

Supervisors: Georgios Smaragdakis, László Erdődi

Detection of critical infrastructure devices on the public Internet

By Martin Mladenov

Earable computing

Supervisors: Przemyslaw Pawelczak, Vivian Dszouza

Chewing Detection on Low Power Embedded Systems

By Cristian Cuţitei

To identify a correlation between IMU and microphone data in earable computing with regards to chewing

By Gregor Figueira Comojo

Detect chewing episodes with an Inertial Measurement Unit (IMU) sensor around the ear

By Vivian Nguyen

Effects of Virtual Reality on Collaboration between Learners

Supervisors: Marcus Specht, Nesse van der Meer

Effects of virtual reality characteristics on collaboration between learners

By Ahmet Hakan Dönmez

A-Maze-ing Arguments in Virtual Reality: An Analysis of the Connection between Shared Situational Awareness and Social Modes of Co-Construction in Virtual Reality

By Brian Rook

Collaborating in Virtual Reality: Exploring the Impact of Visualization of Activities on Social Modes of Co-construction

By Ching Guo

Evaluation of possible connection between Situational Awareness and levels of Social Modes of Co-construction

By Dirk Jan Somsen

Impact of visualizing teammates` actions on the shared situational awareness in virtual reality

By Teresa Gomez Mena

Efficient Video Action Recognition

Supervisors: Jan van Gemert, Ombretta Strafforello, Robert-Jan Bruintjes, Attila Lengyel

Efficient Video Action Recognition: How well does TriDet perform and generalize in a limited compute power and data setting?

By Alexandru Damacus

Benchmarking Data and Computational Efficiency of ActionFormer on Temporal Action Localization Tasks

By Jan Warchocki

Efficient Temporal Action Localization model development practices

By Paul Misterka

TemporalMaxer Performance in the Face of Constraint: A Study in Temporal Action Localization

By Teodor-Gabriel Oprescu

Efficient Temporal Action Localization via Vision-Language Modelling

By Yunhan Wang

Eliciting personal values from the users to build responsible AI

Supervisors: Catholijn Jonker, Pei-Yu Chen

Accuracy of Textual Interfaces using Comparative Questions to Elicit Personal Value-Related Information

By Beatrice Vizuroiu

The Accuracy of an Audio Interface Designed for Value Elicitation

By Elvira Voorneveld

Designing Graphical User Interface To Elicit Personal Values

By Martynas Krupskis

Evaluating the Accuracy of User Values Elicited through a Textual Interface

By Pien Kastelein

Eliciting personal values through isolation questioning: A graphical interface approach

By Selena Mendez

Estimating Intentions to Speak in Social Settings

Supervisors: Hayley Hung

Estimating intentions to speak using Lexical information

By Ferhan Yildiz

Estimating Intention To Speak Using Non-Verbal Vocal Behavior

By Julie van Marken

Estimating Intentions to Speak Using Body Postures in Social Interactions

By Luning Tang

Inferring Segments of Speaking Intention Using a Body-worn Accelerometer

By Nils Achy

Estimating Intentions to Speak Using Multimodal Data

By Waded Oudhuis

Evaluating Robustness of Deep Reinforcement Learning for Autonomous Driving

Supervisors: Matthijs Spaan, Moritz Zanger

Effects of partial observability solver methods on algorithm training and robustness in the domain of autonomous driving

By Ata Ertug Çil

How does entropy maximization affect the training and robustness of final policies under various testing conditions

By Bartu Mehmet Ortal

Comparative Analysis of Exploration Algorithms in Deep Reinforcement Learning for Autonomous Driving

By Efe Sözen

Effects of domain randomization on training and robustness

By Ege Bayram

Effects of action space discretization and DQN extensions on algorithm robustness and efficiency

By Mehmet Alp Sozuduz

Evolutionary Intelligence for Fuzzing and Automatically Testing JavaScript Programs

Supervisors: Annibale Panichella, Mitchell Olsthoorn, Dimitri Stallenberg

Augmenting Pareto Corner Search Evolutionary Algorithm for Automatic Test Case Generation

By Alp Guneri

Performance of the Pareto Envelope-Based Search Algorithm - II in Automated Test Case Generation

By Apoorva Abhishek

Is PSO a valid option for search-based test case generation in the context of dynamically-typed languages?

By Diego Viero

Investigating the performance of SPEA-II on automatic test case generation

By Erwin Li

Can RVEA with DynaMOSA features perform well at generating test cases?

By Sergey Datskiv

Examining and evaluating agent-based social skills training systems

Supervisors: Willem-Paul Brinkman, Mohammed Al Owayyed

The noticeability of behavioral changes of a conversational agent

By Ashma Zaheer

Agent-Based Social Skills Training Systems: A Comprehensive Analysis of Commercial Solutions

By Nuno Afonso Catarino Antunes

Evaluation of feedback generated from agent-based social skills training systems

By Nikola Ntasi

Evaluating the Believability of the Lilobot Conversational Agent

By Vlad Makarov

Exploring Automatic Translation between Affect Representation Schemes

Supervisors: Chirag Raman, Bernd Dudzik

Exploring automatic translation between affect representation schemes of music affective content

By “Alissia” “Rugina”

Exploring automatic translation between affect representation schemes - Video content analysis

By “Ivan” “Dimitrov”

Exploring automatic translation between affect representation schemes - Text content analysis

By “Mira” “Ilieva”

Exploring Automatic Translation between Different Affect Representation Schemes: Affective Image Content Analysis

By “Shuang” “Liu”

Federated Learning: a Comparison of Methods

Supervisors: Marcel Reinders, Swier Garst

How do different machine learning algorithms compare against each other?

By Emils Sipols

Aggregation algorithms comparison

By Roy Katz

How do different Federated Learning frameworks compare?

By Vlad Cristea

Find biological markers for human disease and allergies

Supervisors: Thomas Abeel, Eric van der Toorn, David Calderon Franco

Finding Biomarkers for Type 2 Diabetes

By Aratrika Das

Finding biological markers for the prediction of colorectal cancer

By Jos Sloof

Finding biological markers for Parkinson's disease

By Marilotte Koning

Identifying biological markers in the gut microbiome associated with celiac disease using machine learning

By Petr Persianov

Finding Biomarkers for Schizophrenia

By Timothy Bastow

Flexibility and (dis)aggregation in smart grids

Supervisors: Luciano Cavalcante Siebert, Sietze Kuilman

Aggregation and Prediction of Energy Consumption Data

By Lennard Timp

Partial Hierarchy Appliance Modelling In Household Energy Consumption

By Maurits Kienhuis

Disaggregation of Community Level Energy Data to Individual Households

By Stan Verlaan

Aggregation of energy consumption forecasts across spatial levels

By Twan Borst

Improving the Generalisability of Deep Learning NILM Algorithms using One-Shot Transfer Learning

By Wim Verschuren

Going beyond Federated Learning

Supervisors: Bart Cox, Jérémie Decouchant

Tailoring Attacks To Federated Continual Learning Models

By Eames Trinh

Using Personalized Federated Learning to train Diffusion Models

By Marios Hadjigeorgiou

Training Diffusion Models with Federated Learning

By Matthijs de Goede

Natural Language Processing and Tabular Data sets in Federated Continual Learning

By Taneshwar Pranav Parankusam

Indoor Location Sensing Using Smartphone Acoustic System

Supervisors: Qun Song

Indoor Location Sensing Using Smartphone Acoustic System: Combining Acoustic and WiFi localization

By Dāvis Kažemaks

Indoor Location Sensing Using Smartphone Acoustic System: Impact of interferences on the performance of acoustic indoor location system

By Filip Biliński

Comparative Study of Passive and Active Acoustic Sensing for Indoor Room Recognition

By Michael Chan

Indoor Location Sensing Using Smartphone Acoustic System: What kind of deep models could be used for indoor location recognition? ...

By Radoslav Sozonov

Optimal data capturing for indoor location sensing

By Roald van Heerde

Interactive Segmentation of 3D Medical Images

Supervisors: Klaus Hildebrandt, Nicolas Chaves-de-Plaza

Comparative analysis of discrete and gradient descent based batch query retrieval methods in active learning

By Arjun Vilakathara

Improving the Random Walker algorithm for interactive 3D medical image segmentation using AI predictions

By Bram Stellinga

Optimization Algorithms for Plane Selection in Interactive 3D Image Segmentation

By Jonas van Marrewijk

Effect of Different Uncertainties in Medical Image Segment Error Estimation

By Sungjin Kim Kim

Investigating Inverse Reinforcement Learning from Human Behavior

Supervisors: Luciano Cavalcante Siebert, Angelo Caregnato Neto

Investigating the Extend to which Inverse Reinforcement Learning can Learn Rewards from Noisy Demonstrations

By Charalampos Perdikis

Effect of Demonstrations with Temporal Biases on Learning Rewards using Inverse Reinforcement Learning

By Mateja Zatezalo

To what extent can Inverse Reinforcement Learning learn rewards from expert demonstrations with loss and risk aversion?

By Meric Ikiz

What are the implications of Curriculum Learning strategy on IRL methods?

By Mikhail Vlasenko

Conflicting demonstrations in Inverse Reinforcement Learning

By Rafaël Labbé

Investigating the modelling assumptions of alert-driven attack graphs

Supervisors: Sicco Verwer, Azqa Nadeem

Investigating the impact of sink state merging on alert-driven attack graphs

By Alexandru Dumitriu

Investigating the impact of PDFA implementation on alert-driven attack graphs

By Ioan-Cristian Oprea

Investigating the Impact of Merging Sink States on Alert-Driven Attack Graphs

By Jegor Zelenjak

Investigating Episode Prioritisation in Alert-Driven Attack Graphs

By Senne Van den Broeck

A cognitive load-based quantification approach of interpretability in attack graphs

By Vlad-Mihai Constantinescu

Literature survey on implementation techniques for type systems

Supervisors: Jesper Cockx, Bohdan Liesnikov

Literature survey on implementation techniques for type systems: Exploring name binding techniques

By Hasan Kocakaya

Dependent Types and Conversion Checking: A literature survey on implementation techniques for type systems

By Maria Khakimova

Literature survey on improving type checker efficiency without altering the surface language

By Martijn Staal

Literature survey on implementation techniques for type systems: Inductive data types and pattern matching

By Pau Faraldos Pijoan

Literature survey of type inference algorithms for statically typed languages

By Saulius Jakovonis

Mining Software Testing Knowledge

Supervisors: Andy Zaidman, Baris Ardic

Mining software testing knowledge from stack overflow

By Dibyendu Gupta

Topic Analysis on Popular Software Testing Books

By Hasan Doruk Ozmetin

Mining Massive Open Online Courses (MOOCs) for Software Testing Knowledge

By Neda Džiugaitė

Dissecting the secrets of software testing education in universities

By Onur Gökmen

Using Newsletters to Analyze Curated Software Testing Content

By Philip De Munck

Multi Agent Reinforcement Learning for Active Wake Control

Supervisors: Mathijs de Weerdt, Greg Neustroev

MADDPG

By Guus van der Schaaf

MF-MARL

By Ion Plămădeală

QMix

By Jasper van Selm

DGN

By Jefferson Yeh

COMA

By Mihai Filimon

Multi-Timestep Optimization with Reinforcement Learning and Bayesian Optimization

Supervisors: Matthijs Spaan, Joery de Vries

Parallel cost-aware optimization of multidimensional black-box functions

By Oliver Sihlovec

An empirical analysis of entropy search in batch bayesian optimisation

By Petre-Alexandru Hautelman

Replacing The Acquisition Function in Bayesian Optimization by a Neural Network

By Shayan Ramezani

NLP and Reinforcement Learning to Generate Morally Aligned Text

Supervisors: Pradeep Murukannaiah, Enrico Liscio, Davide Mambelli

Balancing Multidimensional Morality and Progression: Evaluating the Trade-off for Artificial Agents Playing Text-Based Games

By Bianca Serbanescu

Optimising a Pluralist Definition of Morality for AI Agents in Text-based Games

By Kirsten Timmerman

NeRF as a rendering primitive

Supervisors: Elmar Eisemann, Petr Kellnhofer, Michael Weinmann

Using K-Means clustering to export a NeRF for faster rendering in CG applications while preserving view-dependent appearance

By Jurre Groenendijk

StreamNeRF - Adapting a NeRF Model for Progressive Decoding

By Matei Galesanu

Non-Photorealistic Novel View Synthesis Using Radiance Fields

By Medard Szilvasy

Depth Light Field Training (DeLFT)

By Mihnea Toader

One-Stop Code Shop: Assistance for All Languages

Supervisors: Arie van Deursen, Maliheh Izadi, Jonathan Katzy

Evaluating Large Language Model Performance on User and Language Defined Elements in Code.

By Erik Mekkes

A Cross-Lingual Evaluation of CodeGen's Performance in Code Completion

By Miranda Keeler

Cross-lingual Performance of CodeGPT on the Code Completion Task

By Nadine Kuo

A Study on the Impact of Common Code Structures on CodeParrot’s Autocompletion Performance

By Razvan Mihai Popescu

Person identification using heart rate and activity from consumer-grade wearables

Supervisors: David Tax, Arman Naseri Jahfari, Ramin Ghorbani

Comparative Study of Loss Functions in Personal Identification for Smartwatch Data

By Ege Yümlü

Person identification using heart rate and activity from consumer-grade wearables.

By Jip Harthoorn

Performance of Outlier Detection on Smartwatch Data in Single and Multiple Person Environments

By Luuk Wubben

A study of how outlier detectors can accurately authenticate multiple persons using the heart rate from consumer-grade wearables

By Matei Chiriţă

The effect of recentness of consumer-grade wearable training data on the ability of a Deep Neural Network to identify users

By Niels van der Voort

Readability Assessment & Information Access

Supervisors: Maria Soledad Pera

Performance of Transformer Models in Readability Assessment

By David Sachelarie

Leesbaarheid. An Empirical Exploration of the Applicability of Dutch Traditional Readability Formulas to Texts Targeting Children

By Joris Voogt

Investigating the Use of Phonemes as Readability Signals

By Mark Musa Mitrani Sabah

Reconstruction of Visual Stimuli from Brain Activity using Machine Learning

Supervisors: Xucong Zhang

Identification of subjects from reconstructed images

By Arthur Mercier

Denoising task fMRI data for image reconstructions

By Nikita Smolin

Investigating Effects of Participant Variation on Performance of Visual Stimuli Reconstruction From fMRI Signals Using Machine Learning

By Quan Zheng

Noise Attacks as a First Layer of Privacy Protection in Semantic Data Extraction From Brain Activity

By Thomas Walter

A study of the impact of CNN architecture variation on predicting brain activity using feature-weighted receptive fields

By Vlad Murgoci

Revealing the Secret to Successful Virtual Meetings: How Personality, Social Skills, and More, Impact Conversational Involvement

Supervisors: Catholijn Jonker, Masha Tsfasman

The Influence of Individual Backgrounds on Conversational Involvement in Group Settings

By Ana Hobai

How Personality Traits Impact Conversational Involvement in a Group

By Andy Bo Xuan Li

How Personality, Social Skills, and More Impact Conversational Involvement

By Mathijs Rijm

How Personality, Social Skills, and More Impact Conversational Involvement

By Sebastião de Melo e Silva Blasques de Holtreman

Shining a Light on Material Appearance

Supervisors: Ricardo Marroquim, Yang Chen

Shining a Light on Material Appearance: Mapping NDFs to Heightfields

By Casper Struijk

Approximating a full Bidirectional Reflectance Distribution Function from a slice: Creating a BRDF trough solids of revolution

By Gino Tramontina

Soft Peaks: The effects of smoothing on ray reflections

By Lucas Furer

Computing visibility functions using polygon intersection algorithms

By Marc Ruijs

Solve machine learning with... machine learning!

Supervisors: Sebastijan Dumančić, Tilman Hinnerichs

Solving machine learning with machine learning: Exploiting Very Large-Scale Neighbourhood Search for synthesizing machine learning pipelines

By Auke Sonneveld

Solving ML with ML: Evaluating the performance of the Monte Carlo Tree Search algorithm in the context of Program Synthesis

By Bastiaan Filius

Solving ML with ML: Effectiveness of the Metropolis-Hastings algorithm for synthesizing Machine Learning Pipelines

By Denys Sheremet

Genetic Algorithm-based Program Synthesizer for the Construction of Machine Learning Pipelines

By Mathieu Butenaerts

Solving ML with ML: Effectiveness of A* for synthesizing ML pipelines

By Rémi Lejeune

Squishing Giants: Compressing Language Models for Code

Supervisors: Arie van Deursen, Maliheh Izadi, Ali Al-Kaswan

CodeGPT on XTC: Compressing a CodeGPT Model Using Hybrid Layer Reduction and Extreme Quantisation through Knowledge Distillation

By Aral de Moor

Compressing code generation language models on CPUs: Using Group Lasso pruning and post-training quantization

By Dan Sochirca

Distil-CodeGPT, Distilling Code-Generation Models for Local Use

By Emil Malmsten

Leveraging Efficient Transformer Quantization for CodeGPT: A Post-Training Analysis

By Mauro Storti

Survey of Affect Representation Schemes used in Automatic Affect Prediction

Supervisors: Chirag Raman, Bernd Dudzik

Survey of Affect Representation Schemes for Speech Emotion Recognition

By Aditi Rawat

Affect Representation Schemes Used in Affective Video Content Analysis: A Systematic Literature Review

By Ashika Chakravorty

Survey of Affect Representation Schemes used in Vision-Based Automatic Affect Prediction

By Lucia Serrano Ruber

Affect Representation Schemes used in Music Automatic Affect Prediction

By Natalia Maria Bryła

Survey of Affect Representation Schemes in Physiological Automatic Affect Recognition: A Systematic Literature Review

By Natalia Pietnoczko

TinyML-empowered Visible Light Sensing

Supervisors: Qing Wang, Ran Zhu, Mingkun Yang

Low-Power Gesture Recognition Using Convolutional Neural Networks and Ambient Lighting

By Arne de Beer

Digit recognition with visible light using three photodiodes and 3D-preprocessed data

By Gijs van de Linde

Towards a low-cost air-written character recognition system: Designing an embedded machine learning system to recognise the first 10 letters of the Latin alphabet

By Paco Pronk

A TinyML system for gesture detection using 3D pre-processed data

By Sem van den Broek

Touchless Hand Gesture-Based Digit Recognition: using Light-Sensors, Convolutional Neural Networks and a Microcontroller

By Winstijn Smit

Uncovering the secrets of the Maven Repository

Supervisors: Sebastian Proksch, Mehdi Keshani

Java Build Aspects: An empirical analysis

By Gideon Bot

Analysis of Library Sizes in Maven Central

By Niels Tomassen

Maven Packaging

By Priyam Rungta

Dead Links and Lost Code: Investigating the State of Source Code Repositories in Maven Central Repository Packages

By Tudor-Gabriel Velican

Using Computer Vision To Fake Physics

Supervisors: Ranga Rao Venkatesha Prasad, Kees Kroep

Changing the Degrees of Freedom for a particle filter tracking algorithm based on prior knowledge

By Koen Snijder

Pattern-based pose estimation for Tactile Internet

By Marijn Craenen