Explore the vast range of titles available.

Exploring students’ cognitive abilities has long been an important topic in education. This study employs data-driven artificial intelligence (AI) models supported by explainability algorithms and PSM causal inference to investigate the factors influencing students’ cognitive abilities, and it delved into the differences that arise when using various explainability AI algorithms to analyze educational data mining models. In this paper, five AI models were used to model educational data. Subsequently, four interpretable algorithms, including feature importance, Morris Sensitivity, SHAP, and LIME, were used to globally interpret the results, and PSM causal tests were performed on the factors that affect students’ cognitive abilities. The results reveal that self-perception and parental expectations have a certain impact on students’ cognitive abilities, as indicated by all algorithms. Our work also uncovers that different explainability algorithms exhibit varying preferences and inclinations when interpreting the model, as evidenced by discrepancies in the top ten features highlighted by each algorithm. Morris Sensitivity presents a more balanced perspective, while SHAP and feature importance reflect the diversity of interpretable algorithms, and LIME shows a unique perspective. This detailed observation highlights the practical contribution of interpretable AI algorithms in the field of educational data mining, paving the way for more refined applications and deeper insights in future research.

This paper presents the European regulation of platforms. In its first part, it reconstructs the process by which the concept of ‘platform’ in information technology and marketing have evolved and become a legal concept. This emerged from the mid-2010s, first in amendments of sectoral rules and later in sui generis platform rules. The second part of the paper argues that these rules can be interpreted as an emerging separate area of law, the ‘European platform law’. One of the most important ultimate justifying principles and purposes of this legal corpus is the protection of users. This is achieved through a number of tools, some of which are legal transplants from other legal areas (such as consumer protection), while others are sui generis legal rules created specifically for platforms, such as the protection of user accounts or the explainability and transparency of algorithms.

This study proposes an explainability-driven feature selection framework for phishing website detection using a large-scale, heterogeneous dataset collected from four independent sources. The combined dataset contains approximately 500,000 samples, including 300,000 phishing pages and 200,000 legitimate pages, providing a comprehensive representation of real-world web traffic. To enhance model interpretability and reduce feature redundancy, four explainable artificial intelligence (XAI) techniques—SHAP, LIME, partial dependence plots (PDPs), and permutation importance (PDI)—were applied to rank and analyze feature contributions. The union of all selected features was subsequently refined through a thresholding mechanism, forming the proposed Hybrid Explainability Random Forest Algorithm (HXRF). A Random Forest (RF) classifier was trained using the optimized feature subset and evaluated on an independently sampled set of 2000 webpages. Results demonstrate that HXRF significantly improves classification performance, achieving an accuracy of 98.2%, with balanced precision, recall, and F1 scores. The confusion matrix confirms strong generalization across both phishing and legitimate classes, with minimal false predictions. This work demonstrates that combining multi-method XAI with selective feature filtering produces a compact, interpretable, and highly discriminative feature set capable of robust phishing detection at scale.

【Objective】Accurate estimation of crop evapotranspiration (ETc) is essential for improving irrigation and water resource management. This study aimed to reduce the uncertainty in ETc estimation for winter wheat in the region of Nanjing and improve the efficiency of agricultural water use. 【Method】 Four machine learning models: the Lasso Regression, the Adaptive Boosting (AdaBoost), the Random Forest (RF) and Gradient Boosting Decision Tree (GBDT) were used to calculate ETc using meteorological data measured from 2011 to 2018. Bayesian optimization (BO) was used to fine-tune the model parameters. The calculated results were compared with data measured from lysimeters. Shapley Additive Explanations (SHAP) analysis was used to identify key meteorological factors. A logistic growth model for leaf area index (LAI) based on degree-day and effective accumulated temperature was developed to indirectly estimate ETc. 【Result】 ① The GBDT and RF models outperformed other model, with their R2 values being 0.951 and 0.926,

Artificial intelligence is nowadays a reality. Setting rules on the potential outcomes of intelligent machines, so that no surprise can be expected by humans from the behavior of those machines, is becoming a priority for policy makers. In its recent Communication “Artificial Intelligence for Europe” (EU Commission 2018), for instance, the European Commission identifies the distinguishing trait of an intelligent machine in the presence of “a certain degree of autonomy” in decision making, in the light of the context. The crucial issue to be addressed is, therefore, whether it is possible to identify a set of rules for data use by intelligent machines so that the decision-making autonomy of machines can allow for humans’ traditional informational self-determination (humans provide machines only with the data they decide to), as enshrined in many existing legal frameworks (including, for personal data protection, the EU’s General Data Protection Regulation) (EU Parliament and Council 2016) and can actually turn out to be further beneficial to individuals. Governing the autonomy of machines can be a very ambitious goal for humans since machines are geared first to the principles of formal logic and then—possibly—to ethical or legal principles. This introduces an unprecedented degree of complexity in how a norm should be engineered, which requires, in turn, an in-depth reflection in order to prevent conflicts between the legal and ethical principles underlying humans’ civil coexistence and the rules of formal logic upon which the functioning of machines is based (EU Parliament 2017).

Machine-learning models have demonstrated great success in learning complex patterns that enable them to make predictions about unobserved data. In addition to using models for prediction, the ability to interpret what a model has learned is receiving an increasing amount of attention. However, this increased focus has led to considerable confusion about the notion of interpretability. In particular, it is unclear how the wide array of proposed interpretation methods are related and what common concepts can be used to evaluate them. We aim to address these concerns by defining interpretability in the context of machine learning and introducing the predictive, descriptive, relevant (PDR) framework for discussing interpretations. The PDR framework provides 3 overarching desiderata for evaluation: predictive accuracy, descriptive accuracy, and relevancy, with relevancy judged relative to a human audience. Moreover, to help manage the deluge of interpretation methods, we introduce a categorization of existing techniques into model-based and post hoc categories, with subgroups including sparsity, modularity, and simulatability. To demonstrate how practitioners can use the PDR framework to evaluate and understand interpretations, we provide numerous real-world examples. These examples highlight the often underappreciated role played by human audiences in discussions of interpretability. Finally, based on our framework, we discuss limitations of existing methods and directions for future work. We hope that this work will provide a common vocabulary that will make it easier for both practitioners and researchers to discuss and choose from the full range of interpretation methods.

Recent advances in artificial intelligence (AI) have led to its widespread industrial adoption, with machine learning systems demonstrating superhuman performance in a significant number of tasks. However, this surge in performance, has often been achieved through increased model complexity, turning such systems into “black box” approaches and causing uncertainty regarding the way they operate and, ultimately, the way that they come to decisions. This ambiguity has made it problematic for machine learning systems to be adopted in sensitive yet critical domains, where their value could be immense, such as healthcare. As a result, scientific interest in the field of Explainable Artificial Intelligence (XAI), a field that is concerned with the development of new methods that explain and interpret machine learning models, has been tremendously reignited over recent years. This study focuses on machine learning interpretability methods; more specifically, a literature review and taxonomy of these methods are presented, as well as links to their programming implementations, in the hope that this survey would serve as a reference point for both theorists and practitioners.

Deep learning is a subdiscipline of artificial intelligence that uses a machine learning technique called artificial neural networks to extract patterns and make predictions from large data sets. The increasing adoption of deep learning across healthcare domains together with the availability of highly characterised cancer datasets has accelerated research into the utility of deep learning in the analysis of the complex biology of cancer. While early results are promising, this is a rapidly evolving field with new knowledge emerging in both cancer biology and deep learning. In this review, we provide an overview of emerging deep learning techniques and how they are being applied to oncology. We focus on the deep learning applications for omics data types, including genomic, methylation and transcriptomic data, as well as histopathology-based genomic inference, and provide perspectives on how the different data types can be integrated to develop decision support tools. We provide specific examples of how deep learning may be applied in cancer diagnosis, prognosis and treatment management. We also assess the current limitations and challenges for the application of deep learning in precision oncology, including the lack of phenotypically rich data and the need for more explainable deep learning models. Finally, we conclude with a discussion of how current obstacles can be overcome to enable future clinical utilisation of deep learning.

Although deep reinforcement learning has become a promising machine learning approach for sequential decision-making problems, it is still not mature enough for high-stake domains such as autonomous driving or medical applications. In such contexts, a learned policy needs for instance to be interpretable, so that it can be inspected before any deployment (e.g., for safety and verifiability reasons). This survey provides an overview of various approaches to achieve higher interpretability in reinforcement learning (RL). To that aim, we distinguish interpretability (as an intrinsic property of a model) and explainability (as a post-hoc operation) and discuss them in the context of RL with an emphasis on the former notion. In particular, we argue that interpretable RL may embrace different facets: interpretable inputs, interpretable (transition/reward) models, and interpretable decision-making. Based on this scheme, we summarize and analyze recent work related to interpretable RL with an emphasis on papers published in the past 10 years. We also discuss briefly some related research areas and point to some potential promising research directions, notably related to the recent development of foundation models (e.g., large language models, RL from human feedback).

Research on the ethics of algorithms has grown substantially over the past decade. Alongside the exponential development and application of machine learning algorithms, new ethical problems and solutions relating to their ubiquitous use in society have been proposed. This article builds on a review of the ethics of algorithms published in 2016 (Mittelstadt et al. Big Data Soc 3(2), 2016). The goals are to contribute to the debate on the identification and analysis of the ethical implications of algorithms, to provide an updated analysis of epistemic and normative concerns, and to offer actionable guidance for the governance of the design, development and deployment of algorithms.