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 39 for “"Model Reliability"”.
-
A Data-Based Perspective on Model Reliability
… In such settings, the set of features that a model relies on, or its feature prior, often determines the model’s ultimate reliability. While many factors contribute to a model’s feature prior, recent evidence indicates that the training dataset often plays a pivotal role. This thesis therefore …
-
Integrated System Model Reliability Evaluation and Prediction for Electrical Power Systems: Graph Trace Analysis Based Solutions
A new approach to the evaluation of the reliability of electrical systems is presented. In this approach a Graph Trace Analysis based approach is applied to integrated system models and reliability analysis. The analysis zones are extended from the traditional power system functional zones. The …
-
Improved integration of information to reduce subsurface model bias
Subsurface modeling deals with data-related issues like cognitive and sampling biases, and model-related challenges including statistical assumptions, misspecification, and algorithmic biases. These challenges introduce four critical implications during subsurface modeling. Firstly, subsurface …
-
Communication protocols, queuing and scheduling delay analysis in CANDU SCWR hydrogen co-generation model
… load. CANDU-SCWR hydrogen co-generation model reliability can be analyzed by dynamic flow graph methodology. We have analyzed the CANDU-SCWR feed water integration with the oxygen unit of copper chloride cycle and also conducted an analytical review of the current networked control system …
-
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 …
-
Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation
… a major source of failure for machine learning models. However, evaluating model reliability under distribution shift can be challenging, especially since it may be difficult to acquire counterfactual examples that exhibit a specified shift. In this work, we introduce the notion of a dataset …
-
Seismic site characterization through joint modeling of complementary data functionals, with applications to Santo Domingo, Dominican Republic.
… seismic "site characterization" through joint modeling of horizontal to vertical spectral ratios (HVSR) and surface wave dispersion, performed via refraction microtremor (ReMi). Fitting of data functionals by synthetics is driven by global optimization. The products of this approach are shear …
-
Modelling non-linearity in 3D shapes: A comparative study of Gaussian process morphable models and variational autoencoders for 3D shape data
… variation in 3D data is known to influence the reliability of linear statistical shape models (SSM). This problem is regularly acknowledged, but disregarded, as it is assumed that linear models are able to adequately approximate such non-linearities. Model reliability is crucial for medical …
-
Faithful and fair generative explainers for graph neural networks
… ensuring application safety, and enhancing model reliability. Research in this domain is broadly categorized into two approaches: factual explanation (FE) and counterfactual explanation (CFE). FE focuses on identifying key subgraphs or features that contribute to GNN decisions, while CFE …
-
Reliability Analysis of Carbon Fiber Reinforced Polymer (CFRP) Strengthened Steel Beams
… techniques used to produce the joints. Reliability analysis of adhesively bonded CFRP-to-steel double-lap shear (DLS) joints with thin outer adherends was performed first, to study the bond behavior when dominated by adhesive shear stresses. A comprehensive experimental database of the …
-
Modeling the Geometry of Neural Network Representation Spaces
… and b) methods for controlling what features models learn. Each produces improvements in key characteristics, such as training speed, generalization, and model reliability. Part II studies how to use non-Euclidean geometries to build network architectures that respect symmetries and structures …
-
The Automated Construction and Verification of Physically Plausible Models of Physiological Systems
Computational modelling plays a central role in both academic research and clinical applications. As a result, ensuring model reliability has become increasingly important. Since the introduction of advanced computers in the 1960s, the engineering community has tried to increase the credibility of …
-
Statistical Evaluation of Deep Learning for Event Detection in Time Series: Quantifying Uncertainty, Efficiency, and Adaptation with Applications to Seismic Data
… practices have not kept pace. Deep learning models are often assessed using a few performance metrics computed on benchmark datasets, which ignores important questions about how predictive performance varies with data availability, how uncertainty is communicated in both predictions and …
-
Applying Flinet Deep Learning Model to Fluorescence Lifetime Imaging Microscopy for Lifetime Parameter Prediction
… of this study is to train the existing FLINET model on synthetic data that best represents FLIM images on UMSCC74A cells exposed to different mitochondrial inhibitors and uncouplers. The first part of this study ensured that the models perform well on synthetic datasets. Models were trained and …
-
Multimodality: Models, Algorithms, and Applications
… Notably, our tropical cyclone forecasting models demonstrate performance comparable to the US National Hurricane Center's top models for 24-hour intensity and track forecasts. Moreover, we build integrated predictive-to-prescriptive data-driven frameworks connecting operations research and …
-
How Data Drives ML Models Performance
… the understanding of the effect of the data on model performance and reliability. First, we study how choice of training data affects model performance. We consider a transfer learning setting and present a framework for selecting from a large pool of data a pretraining subset that improves …
-
The development of a multisectoral model for the Thai economy (MUTE)
The MUTE model is a multisectoral model developed for the Thai economy. The structure of the MUTE model resembles 1NFORUM type models consisting of 3 main modules, namely, (1) the real side which estimates 7 components of the final demand, (2) the price - income side which calculates the 5 value …
-
Minimizing uncertainty in cure modeling for composites manufacturing
… and temperature are consistent variables used in models to describe the state of material behaviour development for a thermoset during cure. Therefore, the validity of a cure kinetics model is an underlying concern when combining several material models to describe a part forming process, as is …
-
Quantifying the Expansion of an Invasive Plant Species, Dog-strangling Vine (Vincetoxicum rossicum), in Environmental and Geographic Space Over the Past 130 Years
… accurate predictions of their spread. However, modelling the geographic distribution of invasive species, particularly with methods like correlative species distribution models (SDMs), is challenging. SDMs operate under the assumption that species are in equilibrium with their environment (i.e., …
-
Towards Secure and Resilient Machine Learning Systems
… breakthroughs is the development of transformer models, which leverage the attention mechanism to achieve state-of-the-art performance across various tasks. Transformers serve as the foundation for commercial large language models (LLMs), such as GPT and Claude, driving progress in natural …
Page 1 of 2