Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 22 for “"Transparent AI"”.

  1. Towards Smaller, Lighter, and More Transparent AI

    L'abstract è presente nell'allegato / the abstract is in the attachment

    poli-torino Repository record for Towards Smaller, Lighter, and More Transparent AI (opens in a new tab)

  2. INTERPRETABLE ARTIFICIAL INTELLIGENCE USING NONLINEAR DECISION TREES

    … massive application of artificial intelligence (AI) to automate tasks across various domains. The back-end mechanism with which automation occurs is generally black-box. Some of the popular black-box AI methods used to solve an automation task include decision trees (DT), support vector machines …

    msu Repository record for INTERPRETABLE ARTIFICIAL INTELLIGENCE USING NONLINEAR DECISION TREES (opens in a new tab)

  3. Evaluating End-Users’ Perspectives Toward Explainability in Artificial Intelligence

    The rapid evolution of Artificial Intelligence (AI) algorithms in decision-making has profoundly impacted various fields, offering promising advancements. As these advances have been made, explainability has gained prominence, particularly in areas with direct human impact. As a result, Explainable …

    guelph Repository record for Evaluating End-Users’ Perspectives Toward Explainability in Artificial Intelligence (opens in a new tab)

  4. Knowledge Graph-Based Hybrid Agentic Recommender System for Dietary Microbiome Intervention

    … yet microbiome-targeted dietary strategies remain an underused opportunity for slowing disease progression. Translating complex biomedical evidence into actionable, personalized guidance is difficult because unstructured scientific literature rarely maps cleanly onto structured clinical …

    buffalo Repository record for Knowledge Graph-Based Hybrid Agentic Recommender System for Dietary Microbiome Intervention (opens in a new tab)

  5. Motif-based Graph Neural Networks: Representation, interpretation, and extraction

    … MAGE uses motifs as fundamental elements to explain a trained GNN's overarching behavior. Focusing on motif arrangements rather than atom-by-atom placement prevents the generation of invalid intermediate structures. At the instance level, MotifExplainer employs an attention-based mechanism to …

    iastate Repository record for Motif-based Graph Neural Networks: Representation, interpretation, and extraction (opens in a new tab)

  6. Extracting, predicting, and explaining human visual reasoning

    … performance, an important scientific gap remains: current AI systems have limited ability to model, interpret, or predict human visual reasoning in a way that is both computationally rigorous and explainable. This dissertation contributes toward addressing this gap by developing frameworks …

    missouri Repository record for Extracting, predicting, and explaining human visual reasoning (opens in a new tab) Embargoed until 2026-12-01

  7. Sound Practices in Human Resources: A Critical Analysis of How AI Applicant Screening Tools Are Used with Deaf Individuals in the Hospitality and Tourism Sector

    … Deaf Education, and artificial intelligence (AI) technologies used in hiring practices. The purpose of this research is to identify potential barriers to equitable employment for Deaf and Hard-of-Hearing (DHH) individuals and to propose effective methods for evaluating and assessing AI and …

    usf Repository record for Sound Practices in Human Resources: A Critical Analysis of How AI Applicant Screening Tools Are Used with Deaf Individuals in the Hospitality and Tourism Sector (opens in a new tab)

  8. Sparse and Accurate Models Towards Interpretable Machine Learning

    … finance, and criminal justice, the prevailing "black-box" paradigm has created a critical crisis of transparency. Existing explainable AI efforts largely rely on post-hoc approximations, which often fail to remain faithful to the original model’s logic, creating a dangerous "explanation …

    duke Repository record for Sparse and Accurate Models Towards Interpretable Machine Learning (opens in a new tab)

  9. Computer Vision for Plant Pathology: Integrating Biology with Vision AI

    Crop diseases threaten to trigger cascading failures across global food systems, devastating ecosystems, economies and livelihoods. In such historical agricultural collapses, smallholder farmers in low-resource settings have been disproportionately harmed. As agricultural technology becomes …

    whiterose Download PDF for Computer Vision for Plant Pathology: Integrating Biology with Vision AI (opens in a new tab)

  10. EXPLAINABLE MACHINE LEARNING FOR BIOMEDICAL DIAGNOSTICS: OPTICAL IMAGING AND EEG SIGNAL ANALYSIS

    … identification via artificial intelligence (AI). Nevertheless, conventional analysis methods often rely on basic metrics that drop sensitive biotic differences, and various AI systems are difficult to infer, limiting their clinical reliability and practical use. There is a growing need for …

    lsu-thes Repository record for EXPLAINABLE MACHINE LEARNING FOR BIOMEDICAL DIAGNOSTICS: OPTICAL IMAGING AND EEG SIGNAL ANALYSIS (opens in a new tab)

  11. Ethotic Heuristics in Artificial Intelligence: A Rhetorical Framework for Guiding Responsible Data Design Praxis in Healthcare and Surveillance

    … the convergence of artificial intelligence (AI), human-centered design, and rhetoric across three interconnected essays. This dissertation centers on design heuristics as its primary analytic and unifying framework, drawing from traditions such as Data Feminism and rhetorical inquiry. It …

    waterloo Repository record for Ethotic Heuristics in Artificial Intelligence: A Rhetorical Framework for Guiding Responsible Data Design Praxis in Healthcare and Surveillance (opens in a new tab)

  12. Occupational gender bias in large language models : a multi-level analysis using the OccuBias Dataset

    … that influence employment pathways, including AI-powered résumé screening platforms (e.g., HireVue and LinkedIn Recruiter) and interview preparation tools such as Google’s Interview Warmup. Although these systems are designed to improve efficiency and scalability, they are often trained on …

    oxford-brookes Repository record for Occupational gender bias in large language models : a multi-level analysis using the OccuBias Dataset (opens in a new tab) Embargoed until 2028-04-17

  13. Neural network interpretations as means for model analysis and improvement

    … a wide variety of applications, they mostly remain black-box tools. Replacing hand-crafted feature extraction algorithms with representations learned by deep neural networks increases the gap between the inventor’s intuition of the model’s algorithm and the actual algorithm learned by the model. …

    bu Repository record for Neural network interpretations as means for model analysis and improvement (opens in a new tab)

  14. Personalized Algorithmic Recourse: Towards a human-centric approach for algorithmic contestability

    … systems in high-stakes decision-making domains, such as lending, employment, and legal proceedings, has raised significant concerns about fairness, transparency, and accountability. High-profile cases, such as the racially biased COMPAS algorithm, highlight the potential societal risks of …

    trento Repository record for Personalized Algorithmic Recourse: Towards a human-centric approach for algorithmic contestability (opens in a new tab)

  15. Transparency, Accuracy, & Uncertainty in Human-AI Collaborative Decision-Making for Spacecraft Anomaly Diagnosis

    AI agents are becoming increasingly ubiquitous in a variety of domains, from safety-critical environments to day-to-day activities. These days they are being considered more as a virtual peer rather than a decision-making tool. In the coming years, AI agents will have a key role to play in …

    tamu Repository record for Transparency, Accuracy, & Uncertainty in Human-AI Collaborative Decision-Making for Spacecraft Anomaly Diagnosis (opens in a new tab)

  16. Solutions to Passageways Detection in Natural Foliage with Biomimetic Sonar Robot

    Numerous bats species have evolved biosonar to obtain information from their habitats with dense vegetation. Different from man-made sensors, such as stereo cameras and LiDAR, bats' biosonar has much lower spatial resolution and sampling rates. Their biosonar is capable of reliably finding narrow …

    vt Repository record for Solutions to Passageways Detection in Natural Foliage with Biomimetic Sonar Robot (opens in a new tab)

  17. Machine Learning Approaches for Automated Glaucoma Detection using Clinical Data and Optical Coherence Tomography Images

    … and around 300,000 in Australia, where 50% remain undiagnosed. Untreated glaucoma can lead to blindness. Early detection by Artificial intelligence (AI) is crucial to accelerate the diagnosis process and can prevent further vision loss. Many proposed AI systems have shown promising performance …

    unsw Repository record for Machine Learning Approaches for Automated Glaucoma Detection using Clinical Data and Optical Coherence Tomography Images (opens in a new tab)

  18. Overcoming Challenges for Successful Artificial Intelligence Projects in the Manufacturing Industry

    … in the field of artificial intelligence (AI), such as the accessibility of large-scale data sources as well as the improvement of AI algorithms, and, on the other hand, growing competitive pressure and changing customer needs, many incumbents in the manufacturing sector have embarked on a …

    bayreuth Repository record for Overcoming Challenges for Successful Artificial Intelligence Projects in the Manufacturing Industry (opens in a new tab)

  19. Towards Transparent and Grounded Visual AI Systems

    My research goal is to build transparent and grounded AI systems. More specifically, my research tries to answer the question -- Do deep visual models make their decisions for the "right reasons"? In my dissertation, I try to answer this question in two ways: 1. Visual grounding. Grounding is …

    gatech Repository record for Towards Transparent and Grounded Visual AI Systems (opens in a new tab)

  20. A Multidisciplinary Design and Evaluation Framework for Explainable AI Systems

    … biases that can result in discrimination and unfair decision-making. Explainable Artificial Intelligence (XAI) systems can be a solution to predictable and accountable AI by explaining AI decision-making processes for end users and therefore increase user awareness and prevent bias and …

    tamu Repository record for A Multidisciplinary Design and Evaluation Framework for Explainable AI Systems (opens in a new tab)

Page 1 of 2