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 149 for “"Explainable AI (XAI)"”.

  1. EXPLAINABLE AI (XAI) FOR A MACHINE LEARNING HEART DISEASE PREDICTION MODEL

    Cardiovascular diseases (CVDs) remain the leading cause of mortality worldwide, necessitating the development of accurate and interpretable machine learning (ML) models for early diagnosis and risk assessment (World Health Organization, 2021). While ML algorithms such as logistic regression, …

    csusb Repository record for EXPLAINABLE AI (XAI) FOR A MACHINE LEARNING HEART DISEASE PREDICTION MODEL (opens in a new tab)

  2. Efficient on-device saliency prediction via knowledge distillation and explainable AI (XAI)

    … and interpretability. Thus, by leveraging Explainable AI, insight is provided into how knowledge is transferred from the teacher to the student network under the knowledge distillation method.

    adelaide Repository record for Efficient on-device saliency prediction via knowledge distillation and explainable AI (XAI) (opens in a new tab)

  3. INVESTIGATING COLLABORATIVE EXPLAINABLE AI (CXAI)/SOCIAL FORUM AS AN EXPLAINABLE AI (XAI) METHOD IN AUTONOMOUS DRIVING (AD)

    Explainable AI (XAI) systems primarily focus on algorithms, integrating additional information into AI decisions and classifications to enhance user or developer comprehension of the system's behavior. These systems often incorporate untested concepts of explainability, lacking grounding in the …

    mtu Repository record for INVESTIGATING COLLABORATIVE EXPLAINABLE AI (CXAI)/SOCIAL FORUM AS AN EXPLAINABLE AI (XAI) METHOD IN AUTONOMOUS DRIVING (AD) (opens in a new tab)

  4. Attention to Context is What xAI Needs: A Framework for Generating Context-Dependent Requirements for Human-Centric Explainable AI (xAI)

    … deployment of Artificial Intelligence (AI) systems across vital societal domains have yielded promising results, their opacity - the "black box" problem - poses significant barriers to trust in, accountability of, broad acceptance, and adoption of this transformative technology. While …

    ottawa-retro Repository record for Attention to Context is What xAI Needs: A Framework for Generating Context-Dependent Requirements for Human-Centric Explainable AI (xAI) (opens in a new tab)

  5. Mitigating noise and instability in Industrial Explainable AI using Density-Aware and Complexity-Adjusted Explanations

    … of instability and noise sensitivity in Explainable AI (XAI) within high-stakes manufacturing environments. We review the state of the art, identifying a gap in robust local explanations. We introduce two novel contributions: CESHAP, a complexity-aware feature importance method, and …

    greece Repository record for Mitigating noise and instability in Industrial Explainable AI using Density-Aware and Complexity-Adjusted Explanations (opens in a new tab)

  6. Toward XAI for Intelligent Tutoring Systems : a case study

    … a step toward understanding when explanations of AI-driven hints and feedback are useful in Intelligent Tutoring Systems (ITS). We added an explanation functionality for the adaptive hints provided by the Adaptive CSP (ACSP) applet, an intelligent interactive simulation that helps students learn …

    ubc Repository record for Toward XAI for Intelligent Tutoring Systems : a case study (opens in a new tab) Download PDF for Toward XAI for Intelligent Tutoring Systems : a case study (opens in a new tab)

  7. Útoky na algoritmy AI a obrany proti nim

    Bezpečnost AI a útoky na umělou inteligenci představují komplexní a dosud nedostatečně prozkoumanou problematiku. Cílem této práce je nabídnout ucelený přehled klíčových metod a možných vysvětlení útoků na AI a obran proti nim, aby se toto téma stalo přístupnějším a srozumitelnějším pro širší …

    brno-tech Repository record for Útoky na algoritmy AI a obrany proti nim (opens in a new tab)

  8. AI-Driven Cardiorespiratory Signal Processing: Separation, Clustering, and Anomaly Detection

    This thesis applies artificial intelligence (AI) to separate, cluster, and analyze cardiorespiratory sounds. We recorded a new dataset and developed several AI models, including generative AI methods based on large language models (LLMs) for guided separation, explainable AI (XAI) techniques to …

    mcmaster Repository record for AI-Driven Cardiorespiratory Signal Processing: Separation, Clustering, and Anomaly Detection (opens in a new tab)

  9. Probing Human Visual Strategies Using Interpretability Methods for Artificial Neural Networks

    … visual strategies during object recognition remains a challenge in vision science. Existing psychophysical methods used to investigate these strategies are limited in accurately interpreting human decisions. Recently, artificial neural network (ANN) models, which show remarkable similarities to …

    york Repository record for Probing Human Visual Strategies Using Interpretability Methods for Artificial Neural Networks (opens in a new tab)

  10. Article Search Tool and Topic Classifier

    This thesis focuses on 3 main tasks related to Document Recommendations. The first approach deals with applying existing techniques on Document Recommendations using Doc2Vec. A robust representation of the same is presented to understand how noise induced in the embedding space affects predictions …

    tamu Repository record for Article Search Tool and Topic Classifier (opens in a new tab)

  11. Explainability of multi-modal machine learning and deep learning applications in health

    Artificial Intelligence (AI) continues to be developed and has the potential to be incorporated into health, allowing for more efficient and effective diagnosis. However, many AI models operate as ”black-boxes” in how conclusions are drawn or made, leading to a lack of trust. Explainable AI (XAI) …

    hawaii Repository record for Explainability of multi-modal machine learning and deep learning applications in health (opens in a new tab)

  12. Personalized Explanations of Robot Behavior for Human Users

    AI and robotic agents are becoming increasingly prevalent in sectors such as transportation, manufacturing, and disaster response. As these robots are integrated into existing workflows, it is important for their users to understand and anticipate their actions to ensure efficient human-robot …

    rice Repository record for Personalized Explanations of Robot Behavior for Human Users (opens in a new tab)

  13. UNDERSTANDING MODEL EXPLAINABILITY AND PRIVACY FOR FACIAL RECOGNITION APPLICATIONS

    The use of facial data in AI applications raises privacy concerns and requires trustbuilding through providing explanations. 1) We argue that Explainable AI (XAI) can pose privacy risks. While current model inversion attacks reconstruct input data from model predictions, we exploit model …

    nus Repository record for UNDERSTANDING MODEL EXPLAINABILITY AND PRIVACY FOR FACIAL RECOGNITION APPLICATIONS (opens in a new tab) Download file for UNDERSTANDING MODEL EXPLAINABILITY AND PRIVACY FOR FACIAL RECOGNITION APPLICATIONS (opens in a new tab)

  14. "Ethics, Governance, and Bias Mitigation in AI-Enabled loT Applications: A Focus on Transparency and Fairness

    … of Things (IoT) and Artificial Intelligence (AI) technologies promises to address urban challenges yet raises significant security and ethical concerns. This study emphasizes the need for robust governance frameworks to ensure the ethical deployment of these technologies, focusing on the roles …

    york Repository record for "Ethics, Governance, and Bias Mitigation in AI-Enabled loT Applications: A Focus on Transparency and Fairness (opens in a new tab)

  15. Explainable Autoencoder Deciphering Key Pathways Underlying Cancer Expression Patterns

    … interpretations, we developed a tool, XAE4Exp (eXplainable AutoEn-coder for Expression data), which integrates AE and SHapley Additive exPlanations (SHAP), a flagship technique in the field of eXplainable AI (XAI). It quantitatively evaluates the contributions of each gene to the hidden …

    calgary Repository record for Explainable Autoencoder Deciphering Key Pathways Underlying Cancer Expression Patterns (opens in a new tab)

  16. Post-hoc explainable semantic image segmentation: applications for interpretability and adversarial attacks /

    Explainable AI (XAI) has become increasingly important in computer vision applications. While substantial progress has been made in explainable image classification, XAI in semantic segmentation remains underexplored despite its critical role in healthcare, autonomous systems, and other high-stakes …

    vilnius Repository record for Post-hoc explainable semantic image segmentation: applications for interpretability and adversarial attacks / (opens in a new tab)

  17. Human-in-the-loop and Storytelling-based Explainable Frameworks for the Next Generation of Explainable Ensemble Methods and Artificial Intelligence Techniques

    Artificial intelligence (AI) is being adopted in diverse fields, including medical diagnosis and scientific research, to assist with decision-making thanks to its ability to learn underlying patterns from large amounts of data. However, these advances present a challenge. Modern AI systems, …

    fu-berlin Repository record for Human-in-the-loop and Storytelling-based Explainable Frameworks for the Next Generation of Explainable Ensemble Methods and Artificial Intelligence Techniques (opens in a new tab)

  18. Interactive AI Tutors for Training the Workforce of the Future

    The need to train new workers effectively and upskill the existing workforce is a challenge faced by almost every industry across the globe. The healthcare industry, in particular, is confronting a crisis. The World Health Organization (WHO) projects a shortage of 10 million healthcare workers by …

    rice Repository record for Interactive AI Tutors for Training the Workforce of the Future (opens in a new tab)

  19. Explainable data fusion

    The recent resurgence of Artificial Intelligence (AI), specifically in the context of applications like healthcare, security and defense, IoT, and other areas that have a big impact on human life, has led to a demand for eXplainable AI (XAI). The production of explanations is argued to be a key …

    missouri Repository record for Explainable data fusion (opens in a new tab)

  20. Adversarial Explanations for Text-Based Local Surrogate Models

    … as one of the most commonly referenced tools in explainable AI (XAI) frameworks that is integrated into critical machine learning applications–e.g., healthcare and finance. However, its stability remains little explored, especially in the context of text data, due to the unique challenges when it …

    mississippi Repository record for Adversarial Explanations for Text-Based Local Surrogate Models (opens in a new tab)

Page 1 of 8