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 62 for “"Trustworthy Machine Learning"”.
-
(Un)Trustworthy Machine Learning
Machine learning methods have become a commodity in the toolkits of both researchers and practitioners. For performance and privacy reasons, new applications often rely on third-party code or pretrained models, train on crowd-sourced data, and sometimes move learning to users’ devices. This …
-
Towards Trustworthy Machine Learning Systems
Machine learning (ML) has achieved rapid progress in recent years. At the same time, the growing capability of AI/ML also raises concerns over its reliability and societal impacts. This dissertation investigates the robustness and trustworthiness of a spectrum of ML systems: from discriminative to …
-
Towards trustworthy machine learning with kernels
Machine Learning has become an indispensable aspect of various safety-critical industries like healthcare, law, and automotive. Hence, it is crucial to ensure that our machine learning models function appropriately and instil trust among their users. This thesis focuses on improving the safety and …
-
Algorithmic Foundations of Trustworthy Machine Learning
Machine learning models increasingly inform high-stakes decisions in healthcare, finance, and criminal justice, where knowing when to trust a prediction matters as much as the prediction itself. However, standard training procedures often fail to produce predictions that stakeholders can trust, …
-
Multi-objective approaches towards trustworthy machine learning
… and maintain models that are responsible and trustworthy. Models should not discriminate against certain individuals or a group of individuals (fairness), the decisions should be explainable, and they should be robust to adversarial attacks. Moreover, the trained models should be dynamically …
-
Trustworthy Machine Learning with Deep Generative Models
… decade has witnessed the remarkable progress of machine learning (ML) technologies across diverse domains, especially the deep generative models (DGMs) developed on high-dimensional data. However, as ML systems become integral to critical and sensitive applications, ensuring their trustworthiness …
-
Trustworthy Machine Learning: Specification, Verification, and Explanation
In the rapidly changing landscape of machine learning (ML), advanced models and systems are increasingly deployed in safety-critical domains. Nonetheless, ensuring their reliability remains a persistent challenge. The central difficulty lies in their often complex, opaque, and black-box nature, …
-
Trustworthy machine learning throughout model’s life cycle
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms
-
Trustworthy Machine Learning with Data in the Wild
Recent advances in machine learning (ML) have been largely fueled by models trained on extensive internet-collected datasets. While this approach has yielded remarkable capabilities, it introduces critical vulnerabilities: training data can be untrustworthy, containing harmful content or becoming …
-
Casual and trustworthy machine learning: methods and applications
<p>This work focuses on the intersection of machine learning and causal inference and the way in which the two fields can enhance each other by sharing ideas: utilizing machine learning techniques for the computation of causal quantities, the use of ideas from causal inference for invariant …
-
Towards Trustworthy Machine Learning: An Integer Programming Approach
Despite the proliferation of machine learning (ML) in a multitude of applications, current black-box models, such as deep learning, remain hard to understand, critique, and judge by decision makers. This in turn limits their adoption in high-stakes environments (e.g., credit lending, college …
-
Building trustworthy machine learning systems in adversarial environments
… particularly with the rise of big data and deep learning in the last decade, have greatly improved our daily life and at the same time created a long list of controversies. AI systems are often subject to malicious and stealthy subversion that jeopardizes their efficacy. Many of these issues stem …
-
Towards Trustworthy Machine Learning in High-Stakes Decision Making
… privacy, and fairness. In personalized learning settings, it demonstrates that robustness-induced representations can encode identity-specific patterns, enabling patient membership inference without access to training samples. It also introduces a locally-persistent counterfactual bias …
-
Interpretability and Multiplicity: a Path to Trustworthy Machine Learning
<p>Machine learning has been increasingly deployed for myriad high-stakes decisions that deeply impact people's lives. This is concerning, because not every model can be trusted. Interpretability is crucial for making machine learning models trustworthy. It provides human-understandable reasons for …
-
Toward Trustworthy Machine Learning with Blackbox and Whitebox Methods
<p>With the growing applications of machine learning (ML) in high-stake areas such as autonomous driving, medical assistance, and financial prediction, building trustworthy ML models with reliable performance in novel situations becomes increasingly important. While most existing ML methods achieve …
-
Probabilistic Methods in Trustworthy Machine Learning and Scientific Applications
The growing reliance on machine learning in decision-making and policy formulation necessi-tates the development of frameworks and practices that ensure the trustworthiness of these systems. Trustworthy machine learning involves a comprehensive approach to addressing the multifaceted challenges, …
-
TRUSTWORTHY MACHINE LEARNING FOR MEDICAL IMAGING: FAIRNESS, PERSONALIZATION, AND PRIVACY
Machine learning has become one of the most impactful technologies in medical imaging, enabling expert-level performance across tasks such as disease diagnosis, lesion segmentation, and image interpretation. However, the development and deployment of medical imaging systems face unique challenges …
-
Towards Trustworthy Machine Learning in High-Stakes Decision-Making Systems
Machine learning systems are increasingly applied to tasks of high-stakes decision-making, in areas like healthcare, personal finance, and criminal justice. In these areas, the trustworthiness of the system is essential; beyond just having a high-accuracy tool, a number of other desiderata are …
Page 1 of 4