The invention of neural networks marks a critical milestone in the pursuit of true artificial intelligence. Despite their impressive performance on various tasks, these networks face limitations in... Show moreThe invention of neural networks marks a critical milestone in the pursuit of true artificial intelligence. Despite their impressive performance on various tasks, these networks face limitations in learning efficiently as they are often trained from scratch. Deep meta-learning is one approach to improve the learning efficiency by leveraging prior knowledge and experience. Whilst many succesful deep meta-learning techniques have been proposed, our understanding of the performance of these methods remains limited. In this dissertation, we delve deeper into the underlying principles of these algorithms, and aim to gain a comprehensive understanding of why certain algorithms succeed while others fall short. This allows us to design enhanced deep meta-learning algorithms and reason about the impact of specific design choices on the performance of different algorithms. Moreover, we investigate the integration of theoretical principles into meta-learning algorithms to improve their performance. Overall, we make a small step toward a better understanding of deep meta-learning algorithms, paving the way for more robust and principled meta-learning techniques with broader applicability and superior performance. Show less
Transport inspectorates are looking for novel methods to identify dangerous behavior, ultimately to reduce risks associated to the movements of people and goods. We explore a data-driven approach... Show moreTransport inspectorates are looking for novel methods to identify dangerous behavior, ultimately to reduce risks associated to the movements of people and goods. We explore a data-driven approach to arrive at smart inspections of vehicles. Inspections are smart when they are performed (1) accurate, (2) automated, (3) fair, and (4) in an interpretable manner. We leverage tools from the network science and machine learning domain to encode the behavioral aspect of vehicle’s behavior. Tools used in this thesis include community detection, link prediction, and assortativity. We explore their applicability and provide technical methods. In the final chapter, we also discuss the matter of fairness in machine learning. Show less
The focus of this thesis is on the technical methods which help promote the movement towards Trustworthy AI, specifically within the Inspectorate of the Netherlands.The goal is develop and assess... Show moreThe focus of this thesis is on the technical methods which help promote the movement towards Trustworthy AI, specifically within the Inspectorate of the Netherlands.The goal is develop and assess the technical methods which are required to shift the actions of the Inspectorate to a data-driven paradigm, concretely under a supervised classification framework of machine learning.The aspect of reliability is addressed as a data quality concern, viz. missingness and noise.The aspect of fairness is addressed as a counter to bias in the selection process of inspections.The conclusion is that, whilst no complete solution has yet been suggested, it is possible to address the concerns related to data quality and data bias, culminating in well-performing classification models which are reliable and fair. Show less
Legal professionals spend up to a third of their time doing research. During this research legal information retrieval (IR) helps users find information that is relevant for them. These legal IR... Show moreLegal professionals spend up to a third of their time doing research. During this research legal information retrieval (IR) helps users find information that is relevant for them. These legal IR systems are important because the number of legal documents published online is growing exponentially.This research addresses the question: how can bibliometrics improve common ranking algorithms in legal information retrieval?Chapter 2 focuses on the users of legal IR systems. Users were surveyed to determine whether legal practitioners (searching for themselves) and information professionals (searching for others) have the same perception of relevance. This was done by comparing the factors of relevance they consider then evaluating search results. We found no reason to distinguish between these user groups. With regards to the distinction between legal scholars and legal practitioners, it was determined in Chapter 3 that the usage and citations between scholarly and non-scholarly publications show no reason to create separate rankings users based on their affiliation.Chapter 3 regards the documents in the legal IR system. The citation and usage analysis provided the theoretical insight that citations in legal documents measure part of a broad scope of impact, or relevance, on the entire legal field. Using this information a bibliometric-enhanced ranking variable was created.There are several challenges to evaluating a live domain specific IR system. Chapter 4 deals with these challenges and why common evaluation methods in IR are not applicable. In the end, in Chapter 5, a cost based model is used for evaluation, which shows a reduction of cost for the user.Combining all this information this thesis shows that a bibliometric-enhanced ranking feature that takes into account both usage and citations (two flavors of impact relevance), and increases in influence as the reliability of the data grows (in combination with a recency feature that gives new documents the benefit of the doubt and decreases at the same rate as the bibliometric feature increases), can reduce the cost required from legal professionals (whether practitioner, scholar or legal information professional) to find the point of satisfaction in the completeness ideal/research reality trade-off. Show less
Patients share valuable advice and experiences with their peers in online patient discussion groups. These uncensored experiences can provide a complementaryperspective to that of the health... Show morePatients share valuable advice and experiences with their peers in online patient discussion groups. These uncensored experiences can provide a complementaryperspective to that of the health professional and thereby yield novel hypotheses which could be tested in further rigorous medical research. This thesis focuses on the development of automatic extraction methods to harvest these patient experiences from online patient forums using text mining techniques. We also examine the complementary value of these patient-reported outcomes to traditional sources of medical knowledge for scientific hypothesis generation. Specifically, we focus on the extraction of adverse drug events (i.e., side effects) and coping strategies for dealing with adverse drug events. Show less
We present an extensive study of methods for exactly solving stochastic constraint (optimisation) problems (SCPs) in network analysis. These problems are prevalent in science, governance and... Show moreWe present an extensive study of methods for exactly solving stochastic constraint (optimisation) problems (SCPs) in network analysis. These problems are prevalent in science, governance and industry. Both our proposed solving methods aim to strike a good balance between convenience, generality, and speed. The first method we study is generic and decomposes stochastic constraints into a multitude of smaller local constraints that are solved using a constraint programming (CP) or mixed-integer programming (MIP) solver. However, many SCPs are formulated on probability distributions with a monotonic property, meaning that adding a positive decision to a partial solution to the problem cannot cause a decrease in solution quality. The second method is specifically designed for solving global stochastic constraints on monotonic probability distributions (SCMDs) in CP. Both methods use knowledge compilation to obtain a decision diagram encoding of the relevant probability distributions, where we focus on ordered binary decision diagrams (OBDDs). We discuss theoretical advantages and disadvantages of these methods and evaluate them experimentally. We conclude that, while the decomposition method is easy to implement and can be used to solve and SCP, the global stochastic constraint solves problems faster, and is still widely applicable due to the prevalence of monotonicity in real-world problems. Show less
In this dissertation non-parametric Bayesian methods are used in the application of robotic vision. Robots make use of depth sensors that represent their environment using point clouds. Non... Show moreIn this dissertation non-parametric Bayesian methods are used in the application of robotic vision. Robots make use of depth sensors that represent their environment using point clouds. Non-parametric Bayesian methods can (1) determine how good an object is recognized, and (2) determine how many objects a particular scene contains. When there is a model available for the object to be recognized and the nature of perceptual error is known, a Bayesian method will act optimally.In this dissertation Bayesian models are developed to represent geometric objects such as lines and line segments (consisting out of points). The infinite line model and the infinite line segment model use a non-parametric Bayesian model, to be precise, a Dirichlet process, to represent the number of objects. The line or the line segment is represented by a probability distribution. The lines can be represented by conjugate distributions and then Gibbs sampling can be used. The line segments are not represented by conjugate distributions and therefore a split-merge sampler is used.A split-merge sampler fits line segments by assigning points to a hypothetical line segment. Then it proposes splits of a single line segment or merges of two line segments. A new sampler, the triadic split-merge sampler, introduces steps that involve three line segments. In this dissertation, the new sampler is compared to a conventional split-merge sampler. The triadic sampler can be applied to other problems as well, i.e., not only problems in robotic perception.The models for objects can also be learned. In the dissertation this is done for more complex objects, such as cubes, built up out of hundreds of points. An auto-encoder then learns to generate a representative object given the data. The auto-encoder uses a newly defined reconstruction distance, called the partitioning earth mover’s distance. The object that is learned by the auto-encoder is used in a triadic sampler to (1) identify the point cloud objects and to (2) establish multiple occurrences of those objects in the point cloud. Show less
In this thesis the subject of our investigation is the use of the first legal copy of the notarised reporting deed (“de notariële proces-verbaalakte”) as enforceable verdict in the civil... Show moreIn this thesis the subject of our investigation is the use of the first legal copy of the notarised reporting deed (“de notariële proces-verbaalakte”) as enforceable verdict in the civil proceedings before a private court (arbitration or a binding third-party ruling) under Dutch law. Show less
Nowadays, there is a continuous need for many corporations to renew their business portfolio strategically in anticipation of changes in the business environment (e.g., technological change). The... Show moreNowadays, there is a continuous need for many corporations to renew their business portfolio strategically in anticipation of changes in the business environment (e.g., technological change). The ongoing booming of founding international start-ups suggests that small entrepreneurial teams are an effective means to develop new businesses. Corporations should be able to benefit from this form of self-organized innovation when entering novel business domains for strategic renewal. However, corporations that establish small entrepreneurial teams (corporate ventures) are facing two obstacles. First, corporate ventures often fail for reasons that are not well explored. Second, it remains unclear how the partial successes may be improved to large successes. Although the key success factors remain ambiguous, there is little hope that corporate ventures will be successful without effective management. Since an empirical model for corporate venture management does not exists so far, the thesis formulates and answers the following problem statement: How can corporate management effectively manage corporate ventures? Building on qualitative and quantitative research methodologies, a model for effective corporate venture management is developed and tested statistically in the German IT consulting industry. The research results reveal some of the essential management principles through which corporate management can increase corporate venture success systematically. Show less
