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 206 for “"Model Robustness"”.
-
CAD model robustness assessment and repair
… application can properly interpret the model. This ensures that the receiving system gets a full and accurate NURBS-based representation: the original surfaces, the corresponding full complement of model space trim curves, and the corresponding full complement of parameter space trim …
-
Assessing Model Robustness in Complex Visual Environments
… and operate in broader applications, assessing model robustness across various complex environments has become increasingly crucial. Unlike traditional evaluation schemes calculating model accuracy on the in-distribution test set, the focus of model robustness assessment shifts towards …
-
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
-
Impact of various factors on partial least squares model robustness for nondestructive peach fruit quality assessment
… paired with partial least squares (PLS) modeling, as a field deployable method that can be used to measure preharvest internal fruit quality to produce information quickly and non-destructively. These qualities offer an answer to declining fruit quality and waste. Although promising, the …
-
Enhancing Deep Learning Model Robustness: Insights from Out of Distribution Data Augmentation and an Innovative Image Compression Technique
Deep learning models excel when tested on images within their training distribution. However, introducing minor perturbations like noise or blurring to the model’s input image and presenting it with out-of-distribution (OOD) data can significantly reduce accuracy, limiting real-world appli- …
-
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 …
-
A Robust Data-Driven Framework for Artificial Intelligent Systems
… 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 systems by focusing on two key aspects: data robustness and model …
-
Named Entity Recognition on Social Media
… mitigate performance degradation and improve the model robustness of named entity recognition (NER) systems on social media. In an effort to mitigate performance degradation, we study text and image information extraction and fusion to adapt NER systems to multimodal social media environments. …
-
Distance-Based Statistical Methods for Big Data: Probabilistic Search, Distributional Tuning, and Longitudinal Trajectory Analysis
… related to computational scalability and model robustness. This dissertation develops new statistical methods that address these challenges through a unified perspective centered on the geometric and probabilistic structure of data. The work comprises three studies that advance both …
-
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 …
-
TOWARDS ROBUST COMPUTER VISION USING SYNTHETIC DATA AND GENERATIVE MODELS
… decade by deep neural networks, computer vision models are still not ready for many real-world applications due to insufficient robustness to out-of-distribution (OOD) scenarios. Their good performance on standard benchmarks does not seem to transfer well to deployment environments. The need for …
-
Multi-stage stochastic modelling for global supply chain and logistics under uncertainty
… on the applications of multi-stage stochastic models for global supply chain and logistics, especially in global production planning problems and international air cargo forwarding problems under uncertainties. We first exam a multi-period, multi-product and multi-plant production planning …
-
Analysis of Latent Space Representations for Object Detection
… classification, or segmentation. In a DNN model, the relationship between the features learned by the model from the training data and the features leveraged by the model during test and deployment has motivated the area of feature interpretability studies. The work presented here applies …
-
Adversarial Attacks on Differentially Private Factorization Machines in Recommendation Systems
… networks, and streaming services. However, these models often rely on large amounts of user data, raising significant privacy concerns. Differential Privacy (DP) has emerged as a viable solution that provides privacy guarantees by introducing controlled noise into the model computations. Despite …
-
Overcoming Vocabulary Challenges in Natural Language Processing
… it remains challenging to build language models which appropriately generalize across the world's approximately 7,000 languages and 150 scripts—a challenge which begins from one of the very first steps, designing the model vocabulary. Language models are typically defined over a finite set …
-
Crowd Counting with Wi-Fi Probe Requests: A Selective Information Elements-based Approach Supported by Generative Data Augmentation
… optimization for device counting. A diffusion model generates synthetic tabular data to mitigate the limited availability of labelled data, enhancing model robustness. Experimental results demonstrate improved accuracy in device counting, achieving a V-measure of 0.952, an average silhouette …
-
Μέθοδοι μηχανικής μάθησης για σημασιολογική ανάλυση βίντεο
… with the problems of privacy protection and robustness to adversarial attacks. Supervised, semi-supervised and deep learning algorithms were proposed, in the context of one-class classification, multiclass classification, adversarial attacks and defenses. Novel methodologies that provide …
-
Building Robust Text Classification Models under Provenance Shift: Methods of Adjustment and a Framework for Evaluation
… require adequate amount of data to fully train a model, and also assume no difference between the training data and test data. This may be achievable for problems in the general domain. For example, large datasets exist for computer vision (CIFAR-10, CIFAR-100, etc.) and natural language …
-
NOVEL APPROACHES AND EVALUATION FOR ROBUST MACHINE READING COMPREHENSION
… complex questions. Despite this progress, the robustness of MRC models—their consistency in responding to diverse and challenging inputs—remains a concern. Traditional evaluation metrics fall short in capturing performance under challenging conditions. To address this, our first work introduces …
Page 1 of 11