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 54 for “"Model Robustness"”.
-
Probing, Improving, and Verifying Machine Learning Model Robustness
Machine learning models turn out to be brittle when faced with distribution shifts, making them hard to rely on in real-world deployment. This motivates developing methods that enable us to detect and alleviate such model brittleness, as well as to verify that our models indeed meet desired …
-
Faster and easier: cross-validation and model robustness checks
… tools, such as cross-validation (CV) and robustness checks, that help us understand exactly how trustworthy our methods are. In both cases (CV and robustness checks), a typical workflow follows the pattern of “change the dataset or method, and then rerun the analysis.” However, this …
-
Domain transferability, model robustness and data privacy in modern machine learning systems
Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2027-05-01
-
A causal perspective on model robustness: case studies in health and sensor data
Robustness of predictive deep models is a challenging problem with many implications. It is of particular importance when models are used in safety-critical applications, such as healthcare. However, there is yet to be agreement on a comprehensive definition on what it means for a model to be …
-
On Passive-Scoping as a method for Large Language Model Robustness to Jailbreaks and Adversarial Examples
Artificial Intelligence (AI) and large language models (LLMs) not only present a challenge for adversarial robustness, but also the natural emergence of unwanted capabilities. Current approaches to safeguarding AI and LLMs predominantly rely on explicitly restricting known instances of these. …
-
Understanding Scaled Prediction Variance Using Graphical Methods for Model Robustness, Measurement Error and Generalized Linear Models for Response Surface Designs
… plots, to study three specific design problems: robustness to model assumptions, robustness to measurement error and design properties for generalized linear models (GLM). This dissertation presents a graphical method for examining design robustness related to the SPV values using FDS plots by …
-
Understanding Adversarial Robustness in Deep Learning
This thesis studies the adversarial robustness of deep learning models. Our investigation covers various aspects of this phenomenon, including the development of two new defense algorithms, two new attack algorithms, a novel definition of hierarchical adversarial robustness, and an analysis of how …
-
Noisy with a Chance of Mislabels: A Local and Training Dynamics Perspective on Detecting Label Noise in Deep Classification
… in highstakes domains such as healthcare, where model reliability is critical. Detecting and mitigating the influence of mislabeled data is essential to improving both performance and interpretability. Building on insights from training dynamics, we propose Local Consistency across Training …
-
A Case for Pre-trained Language Models in Systems Engineering
… processing techniques. Pre-trained language models, such as BERT, represent state-of-the-art in the field. This thesis seeks to understand if these pre-trained language models can achieve higher model performance at a lower computational and manpower cost than earlier techniques. The results …
-
Linear Mixed Model Robust Regression
Mixed models are powerful tools for the analysis of clustered data and many extensions of the classical linear mixed model with normally distributed response have been established. As with all parametric models, correctness of the assumed model is critical for the validity of the ensuing inference. …
-
A Differential Geometry-Based Algorithm for Solving the Minimum Hellinger Distance Estimator
… believed to exist in a trade space between robustness and efficiency. This thesis examines the Minimum Hellinger Distance Estimator (MHDE), which is known to have desirable robustness properties as well as desirable efficiency properties. This thesis confirms that the MHDE is simultaneously …
-
Adversarial robustness without perturbations
Models resistant to adversarial perturbations are stable around the neighbourhoods of input images, such that small changes, known as adversarial attacks, cannot dramatically change the prediction. Currently, this stability is obtained with Adversarial Training, which directly teaches models to be …
-
Topics in non-convex optimization and learning
… on convex combinations of samples improves model robustness and generalization, and (2) a good initialization is sufficient for training deep residual networks without normalization. The method in (1), called mixup, is motivated by a data-dependent Lipschitzness regularization of the …
-
Combining adaptive and designed statistical experimentation : process improvement, data classification, experimental optimization and model building
… experimental redundancy as well as greater model robustness. The number of extra runs is minimal because some are common and yet both methods provide estimates of the best setting. The second use of adaptive experimentation is in evolutionary operation. During regular system operation small, …
-
Automated Root Tracing Using Deep Learning
… this process. This thesis applies the DeepLabV3+ model with a confidence weighted approach to segment root structures in soil images. The methodology involves classifying images based on root visibility, cropping images to focus on root regions, and training the DeepLabV3+ model, which employs …
-
The Effect of Model Formulation on the Comparative Performance of Artificial Neural Networks and Regression
… used to construct predictive statistical models, relating one or more independent variables (inputs) to a dependent variable (output). Artificial neural networks can also be constructed and trained to learn these complex relationships, and have been shown to perform at least as well as …
-
Optimizing Machine Learning Performance on Tabular Clinical Data: A Pipeline Approach
… that hinder traditional analysis and model efficacy. Confronting inherent issues like data scarcity, imbalance, noise, and sensitivity, this work introduces a comprehensive, adaptable machine learning pipeline engineered for optimal predictive performance. A distinctive feature of this …
-
Learning Through the Lens of Robustness
… which they were developed. How can we build ML models that are robust and reliable enough for real-world deployment? To answer this question, we first focus on training models that are robust to small, worst-case perturbations of their input. Specifically, we consider the framework of robust …
-
Systems Uncertainty in Systems Biology & Gene Function Prediction
… If the goal is to use this data to infer network models, these sparse datasets can lead to under-determined systems. While model parameter variation and its effects on model robustness has been well studied, most of this work has looked exclusively at accounting for variation only from measurement …
-
Biodiversity Impact of China's Power System Transition From a Life Cycle Perspective
… a spatially explicit life cycle assessment (LCA) model to evaluate the biodiversity impacts of China’s power system by applying three mainstream LCIA methods. The model covers the 2020 baseline and two 2050 scenarios—NDC (National Determined Contribution) and PEAK30—and integrates a province-level …
Page 1 of 3