First Advisor
Dacian Daescu
Term of Graduation
January 2026
Date of Publication
6-1-2026
Document Type
Dissertation
Language
English
Subjects
Explainable AI, Mathematical Optimization, Neural Networks, Sensitivity Analysis
Physical Description
1 online resource ( pages)
Abstract
Understanding how model predictions and training outcomes vary with changes in data, features, and modeling choices is central to explainable artificial intelligence. This dissertation introduces a unified framework for explainability by generalizing classical influence functions to encompass user-defined hyperparameters embedded in the training loss, model architecture, or data representation. By extending influence functions in this way, the framework broadens their applicability and integrates multiple explainability techniques into a single, coherent approach. It provides a common mathematical foundation linking data impact, feature importance, and model design analysis, and supports a broad class of additional explainability analyses beyond these settings. The demonstrated applications are validated across diverse neural network settings. In addition, we evaluate the practical feasibility of the proposed framework for large-scale models. Collectively, this work positions sensitivity analysis via hyperparameter-extended influence functions as a practical and scalable basis for explainability in modern machine learning systems.
Rights
In Copyright. URI: http://rightsstatements.org/vocab/InC/1.0/ This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).
Recommended Citation
Breslin, William, "Improving Explainability and Interpretability of Neural Networks via Hyperparameter-Extended Influence Functions" (2026). Dissertations and Theses. Paper 7116.