Master projects
Here you can find all our available master projects.
Open Projects
-
Show me the path: do people only care about paths?
Paths in graphs are natural, arising in domains as diverse as social networks (e.g., which people are in the same community?), communication networks (e.g., how does information spread via SMS messages?), and literary networks (e.g., which scientific papers are the most influential, in terms …
George Fletcher
More infoSBSourav Bhowmick (NTU Singapore) -
AI for 3D Concrete Printing
Designing 3D printable materials has been, so far, a trial-and-error process dependent on human knowledge and effort; hence time-consuming and wasteful. To predict certain properties of 3DCP, material scientists have used modelling and simulations for decades. While helpful in many ways, models mostly require …
Mykola Pechenizkiy
More infoSBSandra Lucas and Önder Babur -
Continual Reinforcement Learning with Language Instructions
Continual reinforcement learning (CRL) stands as a pivotal paradigm in the AI landscape, fostering the development of adaptive and lifelong learning agents. This project delves into the intersection of CRL and natural language processing within the immersive realm of 3D simulation environments. The integration …
Meng Fang
More info
Tristan Tomilin
-
Exploring the Characteristics of Multi-Party Dialogues
The project delves into the realm of Natural Language Processing (NLP) to analyze, understand, and derive insights from multi-party conversations. This study focuses on unraveling the distinct characteristics, complexities, and patterns within conversations involving more than two participants, aiming to enhance the comprehension and …
Meng Fang
More info
Jiaxu Zhao
-
Transfer Learning for Robot-to-Robot Adaptation
A popular paradigm in robotic learning is to train a policy from scratch for every new robot. This is not only inefficient but also often impractical for complex robots. The project revolves around the exploration and advancement of techniques for transferring policies between different …
Meng Fang
More info
Tristan Tomilin
-
Playing Text-based Games with Large Language Models
The project aims to explore the utilization of sophisticated language models in the domain of text-based games. This endeavor seeks to harness the capabilities of large language models, such as GPT (Generative Pre-trained Transformer), in the context of interactive narratives, text adventures, and other …
Meng Fang
More info
Yudi Zhang
-
Language Agents for Playing Card Games
The project is a pioneering initiative that combines Natural Language Processing (NLP) and Reinforcement Learning (RL) methodologies to create intelligent agents capable of understanding natural language instructions and participating in playing card games. This project aims to develop AI-driven agents that not only comprehend …
Meng Fang
More info
Yudi Zhang
-
Multi-Agent Reinforcement Learning for Cooperative Tasks
Multi-Agent Reinforcement Learning (MARL) is a field in artificial intelligence where multiple agents learn to make decisions in an environment through reinforcement learning. In the context of cooperative tasks, it involves agents working together to achieve common goals, sharing information and coordinating their actions …
Meng Fang
More info
Tristan Tomilin
-
AI for histopathology of melanoma
BackgroundMelanoma is a form of skin cancer that originates in melanin-producing cells known as melanocytes. While other skin cancer types occur more frequently, melanoma is most dangerous due to the high likelihood of metastasis if not treated early. The incidence rate of melanoma has …
Sibylle Hess
More infoMVMitko Veta -
Robust, auto-incremental learning
Incremental learning techniques can solve one task after the next without starting from scratch, every time starting from the model learned on the previous task. A current limitation is that these techniques have hyperparameters, controlling for instance how fast the model can adapt to …
More info
Joaquin Vanschoren
-
Self-growing neural networks: using AutoML to Search for Incremental Learning Architectures
In incremental learning, when a new learning task arrives, a deep neural network is trained to map the input to the output space. As a result, at the end of the learning, we have 𝑡 different states of the learner, each starting from the …
More info
Joaquin Vanschoren
-
Learn like humans: curriculum learning for continual learning
In incremental learning, the learner is presented with a sequence of t learning tasks. These tasks are typically sampled randomly, provided in an arbitrary order, which does not align with the natural learning progression observed in lifelong human learners. In human learning, we typically …
More info
Joaquin Vanschoren
-
Understanding transfer
Transfer is a ubiquitous concept in machine learning. The most common form is transfer learning from big pretrained models (e.g. by finetuning or zero-shot predictions), but it is also present in multi-task learning, meta-learning, and continual learning. Still, we have very little understanding of …
More info
Joaquin Vanschoren
-
NXP: On-device learning/federated learning on limited resource devices
On-device learning/federated learning on limited resource devicesAddressing the following questions from NXP perspective:What is the latest state of the art for embedded on-device learning?How does on-device training differ from a regular (desktop/cloud) backprop-setup?Are approaches using one/few-shot training efficient and competitive?What deployment toolchains exist for …
More info
Joaquin Vanschoren
-
NXP: Domain generalization over radar sensors, configurations and datasets
Domain generalization over radar sensors, configurations and datasetsExplore the extent of domain gaps in Radar DNNs over different sensors and configurations;Investigate & improve sota sensor domain generalization techniques for radar-based ADAS;Leverage data-efficient sensor domain gap mitigation, e.g. via active learning.Contact the TU/e supervisor (Joaquin …
More info
Joaquin Vanschoren
-
NXP: Automatic joint design and optimization of neural networks
Automatic joint design and optimization of neural networksNeural Networks can be made more efficient and more accurate through a wide variety of techniques (Neural Architecture Search, Quantization, Pruning, …), but it is an open question on how and when to leverage these techniques in …
More info
Joaquin Vanschoren
-
NXP: Design and automated optimization of DNNs for radar-based ADAS
Design and automated optimization of DNNs for radar-based ADAS (advanced driver assistance systems)Improving state of the art approaches on object detection, classification, and segmentation in radar spectrum and/or 'point cloud' data with neural network architectures;Leveraging radar-domain specifics to improve reliability or efficiency of the …
More info
Joaquin Vanschoren
-
NXP: Scalable Neural Architecture Search
Neural Architecture Search (NAS) is an attractive methodology to design and optimize good and efficient Neural Networks, but expensive for large scale models and or on high-bandwidth datasets. To enable NAS for a wide variety of domains requires exploring, improving and inventing e.g.:Zero-cost proxies …
More info
Joaquin Vanschoren
-
Counterfactual explanations
I plan to offer a few assignments on counterfactual explanationsCounterfactual explanations on evolving dataFeasibility, actionability and personalization of counterfactual explanationsCounterfactual explanations for spotting unwanted biased in predictive model behaviourValue alignment for counterfactual explanations (in collaboration with Emily Sullivan)Counterfactual explanations for behaviour change
More info
Mykola Pechenizkiy
-
Enhancing Reconstructive Surgery Decision-Making
The goal of this project would be to come up with a transformer or any other smart solution to (in a one sentence oversimplified description) find mappings between an image of the current patient condition, possible surgery actions and preferred outcome image. A more detailed …
More info
Mykola Pechenizkiy
-
Implementing inference algorithms for choice functions
In recent years, imprecise-probabilistic choice functions have gained growing interest, primarily from a theoretical point of view. These versatile and expressive uncertainty models have demonstrated their capacity to represent decision-making scenarios that extend beyond simple pairwise comparisons of options, accommodating situations of indecision as …
Arthur van Camp
More info
Cassio de Campos
-
Generative Random Forests: The Next Level
The work on generative random forests has started, but there is a long way to make them practical. This project aims at studying the drawbacks of such models and improving them with better ensemble ideas, gradient boosting, and/or other techniques already employed with decision …
More info
Cassio de Campos
-
Probabilistic Circuits versus Bayesian networks
This project aims to compare two different types of generative models: tractable probabilistic circuits and Bayesian networks of bounded tree-width, and potentially have tools to translate between them (when possible). Probabilistic circuits have been recently applied to a number of tasks, but there is …
More info
Cassio de Campos
-
Hybrid Bayesian networks
This internal project aims at developing and testing (for example in classification tasks) a generative model based on probabilistic graphical models for domains with continuous and categorical variables. We want to learn both the graph structure and parameters of such models while constraining their …
More info
Cassio de Campos
-
Synthetic data generation for causal learning
An arguably major difficulty for improving causal inferences is the lack of availability of data. While observational data are abundant, interventional data are not. This internal project aims at creating software tools to generate data that can be useful for testing causal learning approaches. …
More info
Cassio de Campos
-
Scalable Implementation of Probabilistic Circuits
This internal project aims at designing and development a usable software package for learning and reasoning with probabilistic circuits. Probabilistic circuits are models which can represent complicated mixture models and their computation circuit can be wide and deep. Because they have a structure which …
More info
Cassio de Campos
-
Algorithms for forward irrelevance with choice functions
In recent years, imprecise-probabilistic choice functions have gained growing interest, primarily from a theoretical point of view. These versatile and expressive uncertainty models have demonstrated their capacity to represent decision-making scenarios that extend beyond simple pairwise comparisons of options, accommodating situations of indecision as …
Arthur van Camp
More info
Cassio de Campos
-
Concepts of independence for choice functions
In recent years, imprecise-probabilistic choice functions have gained growing interest, primarily from a theoretical point of view. These versatile and expressive uncertainty models have demonstrated their capacity to represent decision-making scenarios that extend beyond simple pairwise comparisons of options, accommodating situations of indecision as …
Arthur van Camp
More info
Cassio de Campos
-
Local inference algorithms for choice functions
In recent years, imprecise-probabilistic choice functions have gained growing interest, primarily from a theoretical point of view. These versatile and expressive uncertainty models have demonstrated their capacity to represent decision-making scenarios that extend beyond simple pairwise comparisons of options, accommodating situations of indecision as …
Arthur van Camp
More info
Cassio de Campos
-
Interventional Whittle Sum-Product Networks
Whittle sum-product networks [1] model the joint distribution of multivariate time series by leveraging the Whittle approximation, casting the likelihood in the frequency domain, and place a complex-valued sum-product network over the frequencies. The conditional independence relations among the time series can then be …
More info
Devendra Dhami
-
Dynamic Knowledge Graph Embeddings
Knowledge graph embeddings are an important area of research inside machine learning and has become a necessity due to the importance of reasoning about objects, their attributes and relations in large graphs. There have been several approaches that have been explored and can be …
More info
Devendra Dhami
-
Behavior Cloning for Budgeted Reinforcement Learning
Safety is a core challenge for the deployment of reinforcement learning (RL) in real-world applications [1]. In applications such as recommender systems, this means the agent should respect budget constraints [2]. In this case, the RL agent must compute a policy condition of the …
More info
Thiago Simão
-
Curriculum Learning for Constrained Reinforcement Learning in Contextual MDPs
Sample complexity is one of the core challenges in reinforcement learning (RL)[1]. An RL agent often needs orders of magnitude more data than supervised learning methods to achieve a reasonable performance. This clashes with problems with safety requirements, where the agent should minimize the …
More info
Thiago Simão
-
Learning Decision Trees to Reduce the Sample Complexity of Offline Reinforcement Learning
Reinforcement Learning (RL) deals with problems that can be modeled as a Markov decision process (MDP) where the transition function is unknown. When an arbitrary policy was already in execution, and the experiences with the environment were recorded in a dataset, an offline RL …
More info
Thiago Simão
-
Reinforcement Learning for Configurable Systems
Nowadays, most software systems are configurable, meaning that we can tailor the settings to the specific needs of each user. Furthermore, we may already have some data available indicating each user's preferences and the software's performance under each configuration. This way, we can compute …
More info
Thiago Simão
-
Deriving Valuation Bases to Expand GP-Growth to More EMM Model Classes
See PDF
More info
Wouter Duivesteijn
-
Deriving Upper Confidence Bounds to Expand Monte-Carlo Tree Search to More EMM Model Classes
See PDF
More info
Wouter Duivesteijn
-
Surveying to Bring Order in the Jungle of Supervised Local Pattern Mining Implementations
See PDF
More info
Wouter Duivesteijn
-
-
Expanding Exceptional Model Mining on Unstructured Data
See PDF. As attachment, see also https://wwwis.win.tue.nl/~wouter/MSc/Niels.pdf
More info
Wouter Duivesteijn
-
Finding the Curse of Dimensionality Sweet Spot Between Traditional Clustering and Deep Clustering
See PDF
Wouter Duivesteijn
More info
Sibylle Hess
-
Equivariant Neural Simulators for Probabilistic Fluid Dynamics Simulation
TL;DR: In this project, you will focus on developing a model architecture that can efficiently simulate fluid dynamics, while taking into account the vast amount of domain knowledge in the field in the form of symmetries, as well as the modeling of stochastic effects …
Vlado Menkovski
More info
Koen Minartz
-
Understanding Out-of-distribution Detection
There are numerous methods for out-of-distribution (OOD) detection and related problems in deep learning, see e.g. [1] for an overview. Many of these however only work well in highly fine-tuned settings and are not well understood in broader context. In this project, you would …
Sibylle Hess
More info
Jan Moraal
-
Explaining learned features by generative models
In order to get some insight into the inner workings of deep neural network classifiers, a method that enables the interpretation of learned features would be very helpful. This master project is loosely based on the approach presented in [1], where a GAN is …
Sibylle Hess
More infoWMWil Michiels -
Topics in Deep Clustering
Deep clustering is a well-researched field with promising approaches. Traditional nonconvex clustering methods require the definition of a kernel matrix, whose parameters vastly influence the result, and are hence difficult to specify. In turn, the promise of deep clustering is that a feature transformation …
More info
Sibylle Hess
-
Physics-Informed Neural Simulation of Cellular Dynamics
TL;DR: In this project, you will develop a framework for integrating domain knowledge into generative models for cellular dynamics simulations, and apply the method to (synthetic) data of e.g. cancer cell migration. Project description: Studying the variety of mechanisms through which cells migrate and interact …
Vlado Menkovski
More info
Koen Minartz
-
ML Simulation of Nuclear Fusion reactors
Thermonuclear fusion holds the promise of generating clean energy on a large scale. One promising approach for controlled fusion power generation is the tokamak, a torus-shaped device that magnetically confines the fusion plasma in its vessel. Currently, not all physical processes in these plasmas …
Vlado Menkovski
More info
Yoeri Poels
-
Conditional Generation of Materials for Carbon Capture
n recent years, the urgency of addressing the climate crisis, resulting from escalating greenhouse gas emissions, has increased. A potential solution for the increasing amount of CO2 in the air is carbon capture. Zeolites are potential candidate materials for carbon capture, as they are …
Vlado Menkovski
More infoMPMarko Petkovic -
Evaluating Explanations of Model Predictions
The black-box nature of neural networks prohibits their application in impactful areas, such as health care or generally anything that would have consequences in the real world. In response to this, the field of Explainable AI (XAI) emerged. State-of-the-art methods in XAI define a …
Sibylle Hess
More infoWMWil Michiels -
Physics Informed AI for improved cancer prognosis
In order to metastasize, cancer cells need to move. Estimating the ability for cells to move, i.e. their dynamics, or so-called migration potential, is a promising new indicator for cancer patient prognosis (overall survival) and response to therapy. However, predicting the migration potential from …
Sibylle Hess
More infoSVSecondary supervisors could be Liesbeth Janssen or Mitko Vetka. -
Comparison of E(n)-equivariant GNNs for metamaterial simulation
Soft, porous metamaterials are materials that consist of a flexible base material (e.g., rubber-like material) with pores of a carefully designed shape in it. Under external loading (a pressure applied on the outside surface, mechanical constraints, or other interactions), they deform which in turn …
Vlado Menkovski
More infoOHOndrej Rokos, Fleur Hendriks -
Understanding deep learning: linear vs non-linear models and their dynamics of learning
While deep learning has become extremely important in industry and society, neural networks are often considered ‘black boxes’, i.e., it is often believed that it is impossible to understand how neural networks really work. However, there are a lot of aspects we can and …
More info
Hannah Pinson
-
Understanding deep learning: efficient retraining of networks
Recent work has shown that neural networks, such as fully connected networks and CNNs, learn to distinguish between classes from broader to finer distinctions between those classes [1,2] (see Fig. 1). Figure 1: Illustration of the evolution of learning from broader to finer distinctions between …
More info
Hannah Pinson
-
Understanding deep learning: the initial learning rate
While deep learning has become extremely important in industry and society, neural networks are often considered ‘black boxes’, i.e., it is often believed that it is impossible to understand how neural networks really work. However, there are a lot of aspects we can and …
More info
Hannah Pinson
-
Generative Object Detection Models for Mobile Robotics Applications
Project description:In the dynamic landscape of mobile robotics, object detection remains a foundational challenge, critical for enabling machines to interact intelligently with their surroundings. At Avular, a pioneering mobile robotics company in Eindhoven, we are excited to explore novel and innovative approaches in this …
Jakub Tomczak
More infoBKBart Keulen -
Deep Generative Models for (Conditional) Molecule Generation
Project description:Generative AI has become one of the leading approaches to (conditional) molecule generation. Like Large Language Models can learn (to some degree) rules governing natural language, could Large Chemistry Models learn rules governing atoms (quantum chemistry)? This is the leading research question of …
More info
Jakub Tomczak
-
Sustainable Diffusion Models
Project description:Diffusion Models are deep-learning models that achieve state-of-the-art performance in many image synthesis tasks. They are typically parameterized with UNets and consist of billions of weights. Expressing their weights in float32 leads to models that cannot be easily deployed on edge devices (e.g., …
More info
Jakub Tomczak
-
Large Language Models with Knowledge Graphs
Project description:Large Language Models (LLMs) are well-known for knowledge acquisition from large-scale corpus and for achieving SOTA performance on many NLP tasks. However, they can suffer from various issues, such as hallucinations, false references, made-up facts. On the other hand, Knowledge Graphs (KGs) can …
More info
Jakub Tomczak
-
Sustainable Large Language Models
Project description:Large Language Models (LLMs) are deep-learning models that achieve state-of-the-art performance in many NLP tasks. They typically consist of billions of weights. As a result, expressing weights in float32 leads to models of size at least 1GB. Such large models cannot be easily …
More info
Jakub Tomczak
-
Model Transfer for Offline Reinforcement Learning
Offline Reinforcement Learning (RL) deals with the problems where simulation or online interaction is impractical, costly, and/or dangerous, allowing to automate a wide range of applications from healthcare and education to finance and robotics. However, learning new policies from offline data suffers from distributional shifts …
More info
Maryam Tavakol
-
Long-term Fairness with Offline Reinforcement Learning
One of the main concerns in the recent AI research is that most data-driven approaches preserve the bias or unfairness available in the collected (offline) data in the resulting models, which could lead to harmful social and ethical effects in the society. Fairness-aware machine learning has …
More info
Maryam Tavakol
-
A survey on correlations and similarities for spatiotemporal data
Finding pairs of locations that present interesting correlations or similarities (e.g., in their weather, development rate, or population statistics through time) can provide useful insights in different contexts/domains. For example, if a country observes that two different cities have a high similarity on the …
More info
Odysseas Papapetrou
-
Discovery and maintenance of heavy hitters over sliding windows, in a distributed environment.
Synopses are extensively used for summarizing high-frequency streaming data, e.g., input from sensors, network packets, financial transactions. Some examples include Count-Min sketches, Bloom filters, AMS sketches, samples, and histogram. This project will focus on designing, developing, and evaluating synopses for the discovery of heavy …
More info
Odysseas Papapetrou
-
Detection of similarities and correlations in multidimensional time series
Correlations are extensively used in all data-intensive disciplines, to identify relations between the data (e.g., relations between stocks, or between medical conditions and genetic factors). Most algorithms consider one-dimensional time series. For example, in the context of finance, the time series might represent the …
More info
Odysseas Papapetrou
-
Lagged multivariate correlations
Correlations are extensively used in all data-intensive disciplines, to identify relations between the data (e.g., relations between stocks, or between medical conditions and genetic factors). The 'industry-standard' correlations are pairwise correlations, i.e., correlations between two variables. Multivariate correlations are correlations between three or more …
More info
Odysseas Papapetrou
-
A Counterpart of the Relational Algebra for Matrices
The relational algebra is used under-the-hood in every commercial relational database. Often, however, data is not relational. Indeed, data scientists often deal with matrices instead of relations. A counterpart of the relational algebra for the matrix data model, called MATLANG, has been introduced in …
More info
Robert Brijder
-
Information Extraction from Work Orders for Knowledge Graphs
Company: Marel Location: BoxmeerBackgroundWork order descriptions provided by engineers are of utmost importance in various industries as they serve as essential documentation for maintenance, repairs, and other technical tasks. These descriptions provide detailed information about the required work, including the scope, specifications, and any …
Mykola Pechenizkiy
More info
Zeno van Cauter
-
Information Extraction from user manuals for Knowledge Graphs
Company: Marel Location: BoxmeerBackgroundUser manuals and service manuals play a crucial role in guiding individuals on how to effectively and safely operate and maintain machinery. They serve as invaluable resources, providing step-by-step instructions, troubleshooting tips, and essential information. However, one of the challenges that …
Mykola Pechenizkiy
More info
Zeno van Cauter
-
Efficient Unbiased Training of Large-scale Distributed RL
It is widely known that training deep neural networks on huge datasets improves learning. However, huge datasets and deep neural networks can no longer be trained on a single machine. One common solution is to train using distributed systems. In addition to traditional data-centers, …
Maryam Tavakol
More infoARAli Ramezani-Kebrya -
Prompt Engineering for Large Language Models (taken)
GeneralAn internship at Accenture about prompt engineering for LLMs.RequirementsFrom our students we expect the following: high independence (including proposing own ideas);good understanding of mathematics (algebra, calculus, statistics, probability theory);good programming skills (Python + ML/DL libraries, preferably PyTorch). Thesis templatePlease take a look at this …
More info
Jakub Tomczak
-
Programming Database Theory: Using a theorem prover to formalize database theory
Proving a theorem is similar to programming: in both cases the solution is a sequence of precise instructions to obtain the output/theorem given the input/assumptions. In fact, there are programming languages such as Lean, Coq, and Isabelle that can be used to prove theorems. …
More info
Robert Brijder
-
Peer-to-peer Federated Learning
--update--: This project is now taken by Davis EisaksThe goal of this project is to study how to train a machine learning model in a gossip-based approach, where if two devices (e.g smartwatches) pass each other in the physical space, they could exchange part of …
Mykola Pechenizkiy
More infoTDTim d'Hondt -
Bayesian Federated Learning using node-based BNNs.
Node-based BNNs assign latent noise variables to hidden nodes of a neural network. By restricting inference to the node-based latent variables, node stochasticity greatly reduces the dimension of the posterior. This allows for inference of BNNs that are cheap to compute and to communicate, …
Mykola Pechenizkiy
More infoTDTim d'Hondt -
AutoML for Vision Transformers
Motivation. Recently, vision transformer architecture, ViT, excels at many tasks in computer vision, such as image recognition [1], image segmentation [2], image retrieval [3], image generation [4], visual object tracking [5] or object detection [6]. However, all these different sub-tasks require domain expertise, such as the type, …
Joaquin Vanschoren
More info
Mert Kilickaya
-
ML projects at ASML
ASML has recently re-confirmed there two projects; a couple more will likely be confirmed in the coming weeksXAI in Exceptional Model Mining (--- update --- this project is taken by Yasemin Yasarol)In the semiconductor industry there are different, diverse and unique failure modes that impact …
Mykola Pechenizkiy
More infoTTtbc -
ML projects at Floryn
--- update --- These projects are no longer available. Theonymfi Anogeianaki will work on FairML.1. Bayesian inferenceWe have been doing ‘traditional’ machine learning for years now at Floryn but never investigated Bayesian modeling. We currently make use of probability measures that come from our (frequentist) machine learning …
More info
Mykola Pechenizkiy
-
Data-centric AI - Automated data quality assessment
The success (and the cost) of a machine learning product or project depends to a great extend on the quality of the available data. If the data has significant flaws, it may make a project much more expensive and much more time consuming than …
More info
Joaquin Vanschoren
-
Computational Complexity of Probabilistic Circuits
This internal project aims at studying and devising new bounds for the computational complexity of inferences in probabilistic circuits and their robust/credal counterpart, including approximation results and fixed-parameter tractability. It requires mathematical interest and good knowledge of theory of computation. This is a theoretical …
More info
Cassio de Campos
-
Learning Bayesian Networks in a Single Step
This internal project aims at implementing a new approach to learning the structure and parameters of Bayesian networks. It is mostly an implementation project, as the novel ideas are already established (but never published, so the approach is novel). It requires high expertise in …
More info
Cassio de Campos
-
Personalized research project in graph data management
This is a wildcard for projects in (knowledge) graph data management.If you took EDS (Engineering Data Systems) and liked what we did there, we offer research+engineering projects in the scope of our database engine AvantGraph (AvantGraph.io). Topics include (but not limited to):- graph query …
Nick Yakovets
More info
Bram van de Wall
-
Cheaper drugs by auto-optimizing photo-chemistry
Photo-chemistry is a technique where input chemicals are first ionised and then new molecules are synthesised through interactions with photons. The exact amount of input chemicals is very important to make such reactions run effectively. Currently, Bayesian Optimization is used to find the optimal mixtures, …
More info
Joaquin Vanschoren
-
Never-ending Automated Machine Learning: Surrogate model transfer
There is an infinite number of ways to design a machine learning system, and many careful decisions need to be made based on prior experience. The field of automated machine learning (AutoML) aims to make these decisions in a data-driven, objective, and automated way. …
More info
Joaquin Vanschoren
-
Self-adapting Automated Machine Learning
There is an infinite number of ways to design a machine learning system, and many careful decisions need to be made based on prior experience. The field of automated machine learning (AutoML) aims to make these decisions in a data-driven, objective, and automated way.In …
More info
Joaquin Vanschoren
-
Automated Machine Learning: An indestructible AutoML bot
There are an infinite number of ways to design a machine learning system, and many careful decisions need to be made based on prior experience. The field of automated machine learning (AutoML) aims to make these decisions in a data-driven, objective, and automated way.There …
Joaquin Vanschoren
More info
Pieter Gijsbers
-
Task similarity and transferability in machine learning
Humans are very efficient learners because we can very efficiently leverage prior experience when learning new tasks. For instance, a child first learns how to walk, and then efficiently learns how to run (obviously without starting from scratch).Several areas of machine learning aim to …
Joaquin Vanschoren
More info
Prabhant Singh
-
AutoML: scalable meta-learning and continual learning for Bayesian Optimization
Bayesian Optimization is often used in Automated machine learning to predict which models to evaluate next. It works by learning a 'surrogate model' that is trained on previous models tried and can predict which models are interesting to try next. In all current AutoML …
More info
Joaquin Vanschoren
-
Continual Structure from Motion
Autonomous vehicles and robots need 3D information such as depth and pose to traverse paths safely and correctly. Classical methods utilize hand-crafted features that can potentially fail in challenging scenarios, such as those with low texture [1]. Although neural networks can be trained on …
Bahram Zonooz
More info
Elahe Arani
-
Schema language engineering in AvantGraph
Schema languages are critical for data system usability, both in terms of human understanding and in terms of system performance [0]. The property graph data model is part of the upcoming ISO standards around graph data management [4]. Developing a standard schema language for …
More info
George Fletcher
-
Feature selection, sparse neural networks, truly sparse implementations, and societal challenges
Context of the work: Deep Learning (DL) is a very important machine learning area nowadays and it has proven to be a successful tool for all machine learning paradigms, i.e., supervised learning, unsupervised learning, and reinforcement learning. Still, the scalability of DL models is …
Mykola Pechenizkiy
More info
Ghada Sokar
-
Diversifying attention through randomization in sparse neural networks training
Context of the work: Deep Learning (DL) is a very important machine learning area nowadays and it has proven to be a successful tool for all machine learning paradigms, i.e., supervised learning, unsupervised learning, and reinforcement learning. Still, the scalability of DL models is …
Mykola Pechenizkiy
More info
Ghada Sokar
-
Topics in Continual Lifelong Learning
Nowadays, data changes very rapidly. Every day new trends appear on social media with millions of images. New topics rapidly emerge from the huge number of videos uploaded on Youtube. Attention to continual lifelong learning has recently increased to cope with this rapid data …
Mykola Pechenizkiy
More info
Ghada Sokar
-
Multi-modal Representation Learning and Applications
With the rapid development of multi-media social network platforms, e.g., Instagram, Tiktok, etc., more and more content is generated in the multi-modal format rather than pure text. This brings new challenges for researchers to analyze the user generated content and solve some concrete problems …
Yulong Pei
More info
Tianjin Huang
-
Architectural Analysis of Vision Transformers in Continual Learning
Deep neural networks (DNN) deployed in the real world are frequently exposed to non-stationary data distributions and required to sequentially learn multiple tasks. This requires that DNNs acquire new knowledge while retaining previously obtained knowledge. However, continual learning in DNNs, in which networks are …
Elahe Arani
More info
Bahram Zonooz
-
Human Visual System Inspired Mechanisms for Data Curation
Every second, around 107 to 108 bits of information reach the human visual system (HVS) [IK01]. Because biological hardware has limited computational capacity, complete processing of massive sensory information would be impossible. The HVS has therefore developed two mechanisms, foveation and fixation, that preserve perceptual performance …
Bahram Zonooz
More info
Elahe Arani
-
Human Visual System Inspired Mechanisms for Interpretability
Every second, around 107 to 108 bits of information reach the human visual system (HVS) [IK01]. Because biological hardware has limited computational capacity, complete processing of massive sensory information would be impossible. The HVS has therefore developed two mechanisms, foveation and fixation, that preserve perceptual performance …
Elahe Arani
More info
Bahram Zonooz
-
Human Visual System Inspired Mechanisms for Video Action Recognition/Prediction
Every second, around 107 to 108 bits of information reach the human visual system (HVS) [IK01]. Because biological hardware has limited computational capacity, complete processing of massive sensory information would be impossible. The HVS has therefore developed two mechanisms, foveation and fixation, that preserve perceptual …
Bahram Zonooz
More info
Elahe Arani
-
Online knowledge distillation for self-supervised learning
Self-supervised learning [1, 2] solves pretext prediction tasks that do not require annotations in order to learn feature representations. Recent empirical research has demonstrated that deeper and wider models benefit more from task-agnostic use of unlabeled data than their smaller counterparts; i.e., smaller models …
Bahram Zonooz
More info
Elahe Arani
-
Cardinality estimation for factorized query processing
It is well-known that processing of complex analytical queries over large graph datasets introduces a major pain point - runtime memory consumption. To address this, recently, a method based on factorized query processing (FQP) has been proposed. It has been shown that this method …
More info
Nick Yakovets
-
Deep Clustering: Simultaneous Optimization of Representations and Clustering
Deep clustering is a well-researched field with promising approaches. Traditional nonconvex clustering methods require the definition of a kernel matrix, whose parameters vastly influence the result, and are hence difficult to specify. In turn, the promise of deep clustering is that a feature transformation …
More info
Sibylle Hess
-
Building benchmarks for modern graph databases
There exists a wide variety of benchmarks available for graph databases: both synthetic and real-world-based. However, one important problem with current state of the art in graph database benchmarking is that all of the existing benchmarks are inherently based on workloads from relational databases, …
More info
Nick Yakovets
-
Overcoming data scarcity in visual object detection and recognition tasks with frugal learning
IntroductionThe Observe, Orient, Decide and Act (OODA) loop [1] shapes most modern military warfare doctrines. Typically, after gathering sensor and intelligence data in the Observe step, a common tactical operating picture of the monitored aerial, maritime and/or ground scenario is built and shared among …
Mykola Pechenizkiy
More info
Stiven Schwanz Dias
-
Achieving main-memory query processing performance on secondary storage on graph query workloads
Since DRAM is still relatively expensive and contemporary graph database workloads operate with billion-node-scale graphs, contemporary graph database engines still have to rely on secondary storage for query processing. In this project, we explore how novel techniques such as variable-page sizes and pointer swizzling can …
Nick Yakovets
More info
Bram van de Wall
-
Fairness-aware Influence Minimization for Combating Fake News
Influence blocking and fake news mitigation have been the main research direction for the network science and data mining research communities in the past few years. Several methods have been proposed in this direction [1]. However, none of the proposed solutions has proposed feature-blind …
Mykola Pechenizkiy
More info
Akrati Saxena
-
Social Media Data Analysis - Twitter Case Study
In this project, we will analyze social media dataset to answer interesting questions about human behavior. We aim to study biases using social media data and propose fair solutions. The project also aims to model human behavior on social media (depends on the topic).This …
George Fletcher
More info
Akrati Saxena
-
Fairness in Network Anonymization
In the past 10-15 years, a massive amount of social networking data has been released publicly and analyzed to better understand complex networks and their different applications. However, ensuring the privacy of the released data has been a primary concern. Most of the graph …
Mykola Pechenizkiy
More info
Akrati Saxena
-
Fairness-aware Community Detection Method
In real-world networks, nodes are organized into communities and the community size follows power-law distribution. In simple words, there are a few communities of bigger size and many communities of small size. Several methods have been proposed to identify communities using structural properties of …
George Fletcher
More info
Akrati Saxena
-
Towards Cognitive-inspired Adversarial Training Approach
Deep neural networks (DNN) are achieving superior performance in perception tasks; however, they are still riddled with fundamental shortcomings. There are still core questions about what the network is truly learning. DNNs have been shown to rely on local texture information to make decisions, …
Elahe Arani
More info
Bahram Zonooz
-
Generalizable, fair and explainable default predictors
Context:Financial sector is a tightly regulated environment. All models used in the financial sector, are studied under the microscope of developers, validators, regulators, and eventually the end users – the clients, before these models can be deployed and used.To assess whether a customer should be …
Mykola Pechenizkiy
More infoDDDLL -
Data-Efficient Reinforcement Learning under Constraints
Reinforcement learning (RL) is a general learning, predicting, and decision-making paradigm and applies broadly in many disciplines, including science, engineering, and humanities. Conventionally, classical RL approaches have seen prominent successes in many closed world problems, such as Atari games, AlphaGo, and robotics. However, dealing …
Mykola Pechenizkiy
More info
Danil Provodin
-
Automated Knowledge Graph Generation
The goal of this thesis is to develop techniques to generate knowledge graph(s) (KG) by: recognizing and extracting entities and predicates from selected structural parts of transcriptions of our customer contacts - via chat and call - with our Customer Services center; mapping the …
Mykola Pechenizkiy
More infoKBKPN: Gianluigi Bardelloni -
Dialogue Act Modeling
At KPN we collect the transcriptions of our customer contacts with our Customer Services centers executed via the chat and call channels. The structure of such dialogues is made by a number of classifiable parts some of which always occur, for example greetings, customer …
Mykola Pechenizkiy
More infoKBKPN: Gianluigi Bardelloni -
Advanced root-cause analysis in customer contacts
Customers reach out to KPN for various purposes and one of the easiest way for them is to call customer service. There is already a process of analyzing customer calls to classify correct cause of the call but there are some challenges in terms of …
Mykola Pechenizkiy
More infoKBKPN: Gianluigi Bardelloni -
Input Adaptive Inference for Semantic Segmentation
Neural networks typically consist of a sequence of well-defined computational blocks that are executed one after the other to obtain an inference for an input image. After the neural network has been trained, a static inference graph comprising these computational blocks is executed for …
Bahram Zonooz
More info
Elahe Arani
-
Explaining schema conformance for knowledge graphs: conformance reporting for WikiProjects members
Wikidata is an open collaboratively built knowledge base. In the Wikidata community groups of editors who share interest in specific topics form WikiProjects. As part of their regular work, members of WikiProjects would like to regularly test the conformance of entity data in Wikidata against schemas for entity classes. …
George Fletcher
More infoKUKatherine Thornton, Yale University (USA) -
Improving knowledge graph completeness with schemas: Wikidata and ShEx
In the collaboratively built knowledge base Wikidata some editors would appreciate suggestions of how to improve the completeness of items. Currently some community members use an existing tool, Recoin, described in this paper, to get suggestions of relevant properties to use to contribute additional statements. This process could …
George Fletcher
More infoKUKatherine Thornton, Yale University (USA) -
SIMD-based JSON data processing in a dynamic Language VM
The JSON data format is one of the most popular human-readable data formats, and is widely used in Web and Data-intensive applications. Unfortunately, reading (i.e., parsing) and processing JSON data is often a performance bottleneck due to the inherent textual nature of JSON. Recent …
More info
Daniele Bonetta
-
ML-based compiler auto-tuning in GraalVM
Machine-learning based approaches [3] are increasingly used to solve a number of different compiler optimization problems. In this project, we want to explore ML-based techniques in the context of the Graal compiler [1] and its Truffle [2] language implementation framework, to improve the performance …
More info
Daniele Bonetta
-
Dynamic SQL query compilation in GraalVM
Data processing systems such as Apache Spark [1] rely on runtime code generation [2] to speedup query execution. In this context, code generation typically translates a SQL query to some executable Java code, which is capable of delivering high performance compared to query interpretation. …
More info
Daniele Bonetta
-
ML-based Profile-guided optimization in GraalVM
Profile-guided optimization (PGO) [1] is a compiler optimization technique that uses profiling data to improve program runtime performance. It relies on the intuition that runtime profiling data from previous executions can be used to drive optimization decisions. Unfortunately, collecting such profile data is expensive, …
More info
Daniele Bonetta
-
Sea-of-nodes graphs query and visualization
Language Virtual Machines such as V8 or GraalVM [3] use Graphs to represent code. One example Graph representation is the so-called Sea-of-nodes model [1]. Sea-of-nodes graphs of real-world programs have millions of edges, and are typically very hard to query, explore, and analyze. In …
More info
Daniele Bonetta
-
Developing a measure of query language experience
In the Database group, we like to learn more about students’ understanding of query languages. We often do this through user studies, in which we also ask questions about their prior experience with the language. This prior experience may have a large influence on …
George Fletcher
More info
Daphne Miedema
-
Develop a metric to quantify query formulation problems in SQL
SQL has proven to be difficult for students to use effectively. Various papers have been written on the types and frequencies of SQL errors. However, this does not mean that all errors are equal. Some errors may inhibit query formulation much more than others. …
George Fletcher
More info
Daphne Miedema
-
Robust symbol detection and recognition in piping and instrumentation diagrams
Project description This project is concerned with the recognition of symbols of piping and process equipment together with the instrumentation and control devices that appear on piping and instrumentation diagrams (P&ID). Each item on the P&ID is associated with a pipeline. Piping engineers often receive drawings …
Mykola Pechenizkiy
More info
Stiven Schwanz Dias
-
Battle of the credal networks: strong independence or forward irrelevance?
Bayesian networks are a popular model in AI. Credal networks are a robust version of Bayesian networks created by replacing the conditional probability mass functions describing the nodes by conditional credal sets (sets of probability mass functions). Next to their nodes, Bayesian networks are …
More info
Erik Quaeghebeur
-
Fairness Analysis in Anomaly Detection
In anomaly detection, we aim to identify unusual instances in different applications, including malicious users detection in OSNs, fraud detection, and suspicious bank transaction detection. Most of the proposed anomaly detection methods are dependent on network structure as some specific structural pattern can convey …
Mykola Pechenizkiy
More info
Akrati Saxena
-
Curiosity driven fairness in Reinforcement learning
Reinforcement learning (RL) is a computational approach to automating goal-directed decision making. In this project, we will use the framework of Markov decision processes. Fairness in reinforcement learning [1] deals with removing bias from the decisions made by the algorithms. Bias or discrimination in …
Mykola Pechenizkiy
More info
Pratik Gajane
-
Generate fair (pseudo) samples for reinforcement learning
Reinforcement learning (RL) is a computational approach to automating goal-directed decision making. Reinforcement learning problems use either the framework of multi-armed bandits or Markov decision processes (or their variants). In some cases, RL solutions are sample inefficient and costly. To address this issue, some …
Mykola Pechenizkiy
More info
Pratik Gajane
-
Causal perspective of fairness in reinforcement learning
Reinforcement learning (RL) is a computational approach to automating goal-directed decision making using the feedback observed by the learning agent. In this project, we will be using the framework of multi-armed bandits and Markov decision processes. Observational data collected from real-world systems can mostly …
Mykola Pechenizkiy
More info
Pratik Gajane
Assigned Projects
-
On Neural Cellular AutomataNov 2023
The design of collective intelligence, i.e. the ability of a group of simple agents to collectively cooperate towards a unifying goal, is a growing area of machine learning research aimed at solving complex tasks through emergent computation [1, 2]. The interest in these techniques …
Erik Quaeghebeur
More info
Gennaro Gala
-
Pimp my BUS: Improving a Minicluster-based Deterministic Pattern Sampling Algorithm for Exceptional Model MiningNov 2023
See PDF. As attachment, see also https://wwwis.win.tue.nl/~wouter/MSc/Bart.pdf
LKLars KuijtenMore info
Wouter Duivesteijn
-
Preventing Beam Pollution: Defining an Empirical Protocol to Improve Beam Search Lattice TraversalOct 2023
See PDF
BSBart SlendersMore info
Wouter Duivesteijn
-
Diversity of recommendations in collaboration with Bol.comFeb 2023
Recommender Systems (RSs) have emerged as a way to help users find relevant information as online item catalogs increased in size. There is an increasing interest in systems that produce recommendations that are not only relevant, but also diverse [1]. In addition to users, increased …
Mykola Pechenizkiy
More info
Hilde Weerts
-
Simulation of Nanopore sequencing (with generative models)Jan 2023
---UPDATE---: This project is now taken by Jonas NiederleNanopore sequencing is a third-generation sequencing method that directly measures long DNA or RNA (Figure 1). The method works by translocating a single DNA strand through a Nanopore in which an electric current signal is measured. The …
More info
Vlado Menkovski
-
Bubble simulation with latent variable modelsNov 2022
--update--: This project is now taken byTijs TeulingsThe topic of the project is simulation of bubbles with deep generative models. Bubbles are a fascinating phenomenon in multiphase flow, and they play an important role in chemical, industrial processes. Bubbles can be simulated well with …
More info
Vlado Menkovski
-
Aspect-based Few-shot classification (Meta-learning)Nov 2022
--- UPDATE ---: This project is now taken by Tim van EngelandMeta-learning (also referred to as learning to learn) is a set of Machine Learning techniques that aim to learn quickly from a few given examples in changing environments [1]. One instantiation of the meta-learning …
More info
Vlado Menkovski
-
A feasibility study on automated database exercise generation with large language modelsNov 2022
Your lecturers here at the university spend a lot of time creating new exercises for our students, both for weekly assignments as for exams. If you extrapolate this to universities and professional training globally, this is a tremendous effort and use of time. It …
WAWillem Aerts
George Fletcher
More info
Daphne Miedema
-
Analyzing progression of question difficulty for SQL questions on Stack OverflowNov 2022
SQL is difficult to use effectively, and creates many errors. Error types and frequency in SQL have been analyzed by various researchers, such as Ahadi, Prior, Behbood and Lister, and Taipalus and Siponen. One method of problem solving that computer scientists apply is posting …
BWBert Wijnhoven
George Fletcher
More info
Daphne Miedema
-
CHIL-M: CHallenges in analyzing Incomplete Longitudinal Medical dataNov 2022
--- Subproject 1 has been filled. Subproject 2 is still open.In this project, we work together with the Dutch south-west Early Psoriatic Arthritis Registry (DEPAR) which is a collaboration of 15 medical centers in the Netherlands that aim to investigate which patient characteristics, measurements …
VTVictoria Tascau
Rianne Schouten
More info
Wouter Duivesteijn
-
Exceptional Gestalt Mining (EGM)Nov 2022
See PDF
PRPim Rietjens
Wouter Duivesteijn
More infoTBThomas C. van Dijk, Ruhr-Universität Bochum -
Generating Missing At Random (MAR) data in Images; a Convolutional ApproachNov 2022
See PDF
SHSam Al Habash
Wouter Duivesteijn
More info
Vlado Menkovski
Finished Projects
-
Multi-fidelity Simulation Optimization for Large-scale Problems with Input UncertaintyApr 2024
Simulation plays an important role in analyzing complex industrial systems when analytical solutions are unavailable. It has been successfully applied to a variety of areas, such as supply chain systems, healthcare systems, and manufacturing systems.Simulation optimization, i.e., the search for a design or solution …
Maryam Tavakol
More infoMSMohsen Jafari Songhori -
Plausible Counterfactual Scenario Generation for Explainable AI in Psychosis Prognosis PredictionNov 2023
Introduction: Artificial intelligence (AI) has shown great promise in different domains including the clinical domain. However, the applications of the developed AI model in clinical practices remained limited mainly due to the lack of model explainability. Clinicians, in general, want to know why an …
Maryam Tavakol
More infoDKDr. Seyed Mostafa Kia -
k-Nearest Neighbor Imputation Under Monotonicity ConstraintsNov 2023
See PDF
IVIko Vloothuis
Wouter Duivesteijn
More info
Rianne Schouten
-
Execution and Visual Representations of SQL queries in case of syntax errorsSep 2023
Query formulation in SQL is difficult for novices, and many errors are made in query formulation. Existing research has focused on registering error types and frequencies. Not much attention has been paid to solving these problems. One of the problems in SQL is with …
BWBas Witters
George Fletcher
More info
Daphne Miedema
-
Efficient surrogates for the Ainslie wind turbine wake modelAug 2023
In wind farms, one source of reduction in power generation by the turbines is the reduction of wind speed in the wake downstream of each turbine's rotor. Namely, a turbine downstream in the wind direction of another will effectively experience wind with a reduced …
Erik Quaeghebeur
More infoLBLaurens Bliek (Information Systems, IE&IS) -
Object measurement by using computer vision (at a company)Aug 2023
Company: Datacation / aerovision.aiLocation: Eindhoven (AI Innovation Center at High Tech Campus) or Amsterdam (VU)Project descriptionAerovision.ai is a start-up that is building a no-code A.I. platform for drone companies. With this A.I. platform, companies can train, deploy and evaluate their customized computer vision algorithms, …
Jakub Tomczak
More infoACAt the company -
Multivariate correlations for data cleaningJul 2023
Correlations are extensively used in all data-intensive disciplines, to identify relations between the data (e.g., relations between stocks, or between medical conditions and genetic factors). The 'industry-standard' correlations are pairwise correlations, i.e., correlations between two variables. Multivariate correlations are correlations between three or more variables. …
More info
Odysseas Papapetrou
-
Correlation Detective on streaming dataJul 2023
Correlations are extensively used in all data-intensive disciplines, to identify relations between the data (e.g., relations between stocks, or between medical conditions and genetic factors). The 'industry-standard' correlations are pairwise correlations, i.e., correlations between two variables. Multivariate correlations are correlations between three or more variables. …
More info
Odysseas Papapetrou
-
Efficient Granger causalityJul 2023
Granger causality is among the standard functions for quantifying causal relationships between time series (e.g., closing prices of stocks). However, naïve computation of Granger causality requires pairwise comparisons between all time series, which comes with quadradic complexity. In this project you will focus on …
More info
Odysseas Papapetrou
-
(self-defined project on model-centric SD)Jul 2023
(irrelevant for self-defined project)
NSNiels SchellemanMore info
Wouter Duivesteijn
-
(self-proposed project on time-dependent SD)Jul 2023
(irrelevant)
BEBart EngelenMore info
Wouter Duivesteijn
-
Identifying robust instances in classificationJul 2023
In a classification task, some instances are classified more robustly than others. Namely, even with a large modification of the training set, these instances (in the test set) will be assigned to the same class. Other instances are non-robust in the sense that a …
More info
Erik Quaeghebeur