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 10 of 10 for “"Robust AI Systems"”.

  1. A Robust Data-Driven Framework for Artificial Intelligent Systems

    Artificial Intelligence (AI) systems have demonstrated remarkable performance across various domains. However, their robustness remains a critical concern, particularly in terms of data and model reliability. This dissertation aims to address the challenges associated with building robust AI …

    usf Repository record for A Robust Data-Driven Framework for Artificial Intelligent Systems (opens in a new tab)

  2. From evolving graphs to irregular time series : learning across structure and time

    … evolving graphs. We propose a contrastive self-training approach for incremental unsupervised domain adaptation, where non-stationary graph distributions cause deployed graph neural networks (GNN) to degrade. We further address novel node category detection under subpopulation shift, where shifts …

    texas Repository record for From evolving graphs to irregular time series : learning across structure and time (opens in a new tab)

  3. Towards reliable machine learning for ultrasound screening of aortic stenosis

    … valve disorder, requires early detection but remains difficult to diagnose in routine practice. Although echocardiography with Doppler imaging is the clinical standard, these assessments are typically limited to trained specialists. Point-of-care ultrasound (POCUS) offers an accessible …

    ubc Repository record for Towards reliable machine learning for ultrasound screening of aortic stenosis (opens in a new tab) Download PDF for Towards reliable machine learning for ultrasound screening of aortic stenosis (opens in a new tab)

  4. Minimizing label dependence in artificial intelligence for cancer surgery

    The integration of Artificial Intelligence (AI) into surgical oncology holds transformative potential for improving diagnostic accuracy and workflow efficiency. However, the practical deployment of these systems is severely constrained by the scarcity of high-quality labelled data, particularly for …

    queens Repository record for Minimizing label dependence in artificial intelligence for cancer surgery (opens in a new tab)

  5. A Research on LLM Generated Feedback Interpretability and Image Labeling Sketch Features

    The accuracy of training data directly impacts the performance of lots of applications powered by machine learning models, influencing their ability to make reliable predictions. In industries such as transportation, healthcare, and robotics, precise image labeling is essential for building robust …

    tamu Repository record for A Research on LLM Generated Feedback Interpretability and Image Labeling Sketch Features (opens in a new tab) Embargoed until 2027-05-01

  6. Improving the Performance and Robustness of NLP models with Contrastive Data and Learning

    … examples, which leads to more high-quality, robust and generalizable representations. Contrastive learning has also been widely used to improve the performance and robustness of natural language processing (NLP) models across different tasks. While extensively explored, existing contrastive …

    adelaide Repository record for Improving the Performance and Robustness of NLP models with Contrastive Data and Learning (opens in a new tab)

  7. Integrating Artificial Intelligence for Transportation Cyber-Physical Systems: From Detection to Cyber Resilience

    … warming. The first part of the dissertation aims to create a cost-effective system for real-time methane detection and intensity prediction using ensemble learning models trained on meteorological parameters. The ensemble learning-based classification models show a high accuracy for methane …

    clemson Repository record for Integrating Artificial Intelligence for Transportation Cyber-Physical Systems: From Detection to Cyber Resilience (opens in a new tab)

  8. Towards More Human-like Multi-Modal Understanding and Prediction using Novel Benchmark, Evaluation Frameworks and Modeling Strategies

    Recent advances in artificial intelligence (AI) have pushed the field to achieve remarkable heights in areas such as image recognition, scanpath prediction, and other multimodal tasks. However, despite these successes, today's AI systems still struggle to emulate the performance of human cognition …

    umn Repository record for Towards More Human-like Multi-Modal Understanding and Prediction using Novel Benchmark, Evaluation Frameworks and Modeling Strategies (opens in a new tab)

  9. BETTER MODELS FOR HIGH-STAKES TASKS

    … In this work, we present several methods that aim to improve machine learning models in high-stakes environments like healthcare. Our work unifies two sub-fields of machine learning, explainable AI, and uncertainty quantification. First we develop a model-agnostic approach to deliver …

    rowan Repository record for BETTER MODELS FOR HIGH-STAKES TASKS (opens in a new tab)

  10. Rating AI Models for Robustness Through a Causal Lens

    As Artificial Intelligence (AI) systems become increasingly powerful and widely accessible, trustworthiness remains a major barrier to their adoption in critical domains such as finance and healthcare. With the advent of large language models (LLMs) that can perform multiple tasks with strong …

    south-carolina Repository record for Rating AI Models for Robustness Through a Causal Lens (opens in a new tab)