We present a novel architecture for an AI system that allows a priori knowledge to combine with deep learning. In traditional neural networks, all available data is pooled at the input layer. Our alternative neural network is constructed so that partial representations (invariants) are learned in the intermediate layers, which can then be combined with a priori knowledge or with other predictive analyses of the same data. This leads to smaller training datasets due to more efficient learning. In addition, because this architecture allows inclusion of a priori knowledge and interpretable predictive models, the interpretability of the entire system increases while the data can still be used in a black box neural network. Our system makes use of networks of neurons rather than single neurons to enable the representation of approximations (invariants) of the output.
LINK
Background: Previous studies found that 40-60% of the sarcoidosis patients suffer from small fiber neuropathy (SFN), substantially affecting quality of life. SFN is difficult to diagnose, as a gold standard is still lacking. The need for an easily administered screening instrument to identify sarcoidosis-associated SFN symptoms led to the development of the SFN Screening List (SFNSL). The usefulness of any questionnaire in clinical management and research trials depends on its interpretability. Obtaining a clinically relevant change score on a questionnaire requires that the smallest detectable change (SDC) and minimal important difference (MID) are known. Objectives: The aim of this study was to determine the SDC and MID for the SFNSL in patients with sarcoidosis. Methods: Patients with neurosarcoidosis and/or sarcoidosis-associated SFN symptoms (N=138) included in the online Dutch Neurosarcoidosis Registry participated in a prospective, longitudinal study. Anchor-based and distribution-based methods were used to estimate the MID and SDC, respectively. Results: The SFNSL was completed both at baseline and at 6-months’ follow-up by 89/138 patients. A marginal ROC curve (0.6) indicated cut-off values of 3.5 points, with 73% sensitivity and 49% specificity for change. The SDC was 11.8 points. Conclusions: The MID on the SFNSL is 3.5 points for a clinically relevant change over a 6-month period. The MID can be used in the follow-up and management of SFN-associated symptoms in patients with sarcoidosis, though with some caution as the SDC was found to be higher.
DOCUMENT
Remaining Useful Life (RUL) estimation is directly related with the application of predictive maintenance. When RUL estimation is performed via data-driven methods and Artificial Intelligence algorithms, explainability and interpretability of the model are necessary for trusted predictions. This is especially important when predictive maintenance is applied to gas turbines or aeroengines, as they have high operational and maintenance costs, while their safety standards are strict and highly regulated. The objective of this work is to study the explainability of a Deep Neural Network (DNN) RUL prediction model. An open-source database is used, which is composed by computed measurements through a thermodynamic model for a given turbofan engine, considering non-linear degradation and data points for every second of a full flight cycle. First, the necessary data pre-processing is performed, and a DNN is used for the regression model. The selection of its hyper-parameters is done using random search and Bayesian optimisation. Tests considering the feature selection and the requirements of additional virtual sensors are discussed. The generalisability of the model is performed, showing that the type of faults as well as the dominant degradation has an important effect on the overall accuracy of the model. The explainability and interpretability aspects are studied, following the Local Interpretable Model-agnostic Explanations (LIME) method. The outcomes are showing that for simple data sets, the model can better understand physics, and LIME can give a good explanation. However, as the complexity of the data increases, both the accuracy of the model drops but also LIME seems to have difficulties in giving satisfactory explanations.
DOCUMENT
Meten is weten. Daar zijn we het allemaal over eens. Maar hoe zorg je er voor dat je op het goede moment en met het juiste meetinstrument een zinvolle meting doet? Meten is immers geen doel op zich. Onlangs kwam een nieuwe uitgave van het boek Meten in de praktijk: Stappenplan voor het gebruik van meetinstrumenten in de praktijk uit. Hoog tijd om stil te staan bij meten in de dagelijkse ergotherapiepraktijk en daar een stappenplan voor te presenteren.
DOCUMENT
As urban environments increasingly adopt automated technologies for municipal enforcement, this paper interrogates the erosion of human judgment, discretion, and interaction in public space governance. Drawing on participatory design workshops within the “Human Values for Smarter Cities” project, the authors explore how automation—exemplified by license plate scan cars—amplifies efficiency while marginalizing ambiguity, context, and citizen voice. Through grounded case studies, the essay reveals how automation can produce unintended injustices by failing to accommodate lived realities and interpretative nuance. The paper proposes speculative redesigns aimed at reintroducing “human inefficiency” into automated systems, advocating for real-time interaction, interpretability, and civic negotiation. Situating their critique within broader debates on trust, control, and the human scale, the authors argue for a shift from technocratic solutionism toward relational urban technologies. Ultimately, the work contributes to civic technology discourse by outlining design principles that foreground empathy, discretion, and participatory governance in the age of the smart city.
MULTIFILE
In this post I give an overview of the theory, tools, frameworks and best practices I have found until now around the testing (and debugging) of machine learning applications. I will start by giving an overview of the specificities of testing machine learning applications.
LINK
Trust in AI is crucial for effective and responsible use in high-stakes sectors like healthcare and finance. One of the most commonly used techniques to mitigate mistrust in AI and even increase trust is the use of Explainable AI models, which enables human understanding of certain decisions made by AI-based systems. Interaction design, the practice of designing interactive systems, plays an important role in promoting trust by improving explainability, interpretability, and transparency, ultimately enabling users to feel more in control and confident in the system’s decisions. This paper introduces, based on an empirical study with experts from various fields, the concept of Explanation Stream Patterns, which are interaction patterns that structure and organize the flow of explanations in decision support systems. Explanation Stream Patterns formalize explanation streams by incorporating procedures such as progressive disclosure of explanations or interacting with explanations in a more deliberate way through cognitive forcing functions. We argue that well-defined Explanation Stream Patterns provide practical tools for designing interactive systems that enhance human-AI decision-making.
MULTIFILE
Data-driven modeling is an imperative tool in various industrial applications, including many applications in the sectors of aeronautics and commercial aviation. These models are in charge of providing key insights, such as which parameters are important on a specific measured outcome or which parameter values we should expect to observe given a set of input parameters. At the same time, however, these models rely heavily on assumptions (e.g., stationarity) or are “black box” (e.g., deep neural networks), meaning that they lack interpretability of their internal working and can be viewed only in terms of their inputs and outputs. An interpretable alternative to the black box models and with considerably less assumptions is symbolic regression (SR). SR searches for the optimal model structure while simultaneously optimizing the model’s parameters without relying on an a priori model structure. In this work, we apply SR on real-life exhaust gas temperature (EGT) data, collected at high frequencies through the entire flight, in order to uncover meaningful algebraic relationships between the EGT and other measurable engine parameters. The experimental results exhibit promising model accuracy, as well as explainability returning an absolute difference of 3°C compared to the ground truth and demonstrating consistency from an engineering perspective.
DOCUMENT
Whitepaper: The use of AI is on the rise in the financial sector. Utilizing machine learning algorithms to make decisions and predictions based on the available data can be highly valuable. AI offers benefits to both financial service providers and its customers by improving service and reducing costs. Examples of AI use cases in the financial sector are: identity verification in client onboarding, transaction data analysis, fraud detection in claims management, anti-money laundering monitoring, price differentiation in car insurance, automated analysis of legal documents, and the processing of loan applications.
DOCUMENT
Explainable Artificial Intelligence (XAI) aims to provide insights into the inner workings and the outputs of AI systems. Recently, there’s been growing recognition that explainability is inherently human-centric, tied to how people perceive explanations. Despite this, there is no consensus in the research community on whether user evaluation is crucial in XAI, and if so, what exactly needs to be evaluated and how. This systematic literature review addresses this gap by providing a detailed overview of the current state of affairs in human-centered XAI evaluation. We reviewed 73 papers across various domains where XAI was evaluated with users. These studies assessed what makes an explanation “good” from a user’s perspective, i.e., what makes an explanation meaningful to a user of an AI system. We identified 30 components of meaningful explanations that were evaluated in the reviewed papers and categorized them into a taxonomy of human-centered XAI evaluation, based on: (a) the contextualized quality of the explanation, (b) the contribution of the explanation to human-AI interaction, and (c) the contribution of the explanation to human- AI performance. Our analysis also revealed a lack of standardization in the methodologies applied in XAI user studies, with only 19 of the 73 papers applying an evaluation framework used by at least one other study in the sample. These inconsistencies hinder cross-study comparisons and broader insights. Our findings contribute to understanding what makes explanations meaningful to users and how to measure this, guiding the XAI community toward a more unified approach in human-centered explainability.
MULTIFILE
