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"”.

  1. 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 …

    mit Repository record for Probing, Improving, and Verifying Machine Learning Model Robustness (opens in a new tab)

  2. 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 …

    mit Repository record for Faster and easier: cross-validation and model robustness checks (opens in a new tab)

  3. 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

    uiuc Repository record for Domain transferability, model robustness and data privacy in modern machine learning systems (opens in a new tab)

  4. 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 …

    cambridge Repository record for A causal perspective on model robustness: case studies in health and sensor data (opens in a new tab)

  5. 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. …

    mit Repository record for On Passive-Scoping as a method for Large Language Model Robustness to Jailbreaks and Adversarial Examples (opens in a new tab)

  6. 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 …

    vt Repository record for Understanding Scaled Prediction Variance Using Graphical Methods for Model Robustness, Measurement Error and Generalized Linear Models for Response Surface Designs (opens in a new tab)

  7. 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 …

    toronto-retro Repository record for Understanding Adversarial Robustness in Deep Learning (opens in a new tab)

  8. 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 …

    mit Repository record for Noisy with a Chance of Mislabels: A Local and Training Dynamics Perspective on Detecting Label Noise in Deep Classification (opens in a new tab)

  9. 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 …

    mit Repository record for A Case for Pre-trained Language Models in Systems Engineering (opens in a new tab)

  10. 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. …

    vt Repository record for Linear Mixed Model Robust Regression (opens in a new tab)

  11. 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 …

    vt Repository record for A Differential Geometry-Based Algorithm for Solving the Minimum Hellinger Distance Estimator (opens in a new tab)

  12. 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 …

    mit Repository record for Adversarial robustness without perturbations (opens in a new tab)

  13. 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 …

    mit Repository record for Topics in non-convex optimization and learning (opens in a new tab)

  14. 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, …

    mit Repository record for Combining adaptive and designed statistical experimentation : process improvement, data classification, experimental optimization and model building (opens in a new tab)

  15. 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 …

    gatech Repository record for Automated Root Tracing Using Deep Learning (opens in a new tab)

  16. 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 …

    odu Repository record for The Effect of Model Formulation on the Comparative Performance of Artificial Neural Networks and Regression (opens in a new tab)

  17. 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 …

    uic

  18. 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 …

    mit Repository record for Learning Through the Lens of Robustness (opens in a new tab)

  19. 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 …

    vt Repository record for Systems Uncertainty in Systems Biology & Gene Function Prediction (opens in a new tab)

  20. 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 …

    exeter

Page 1 of 3