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 43 for “"black-box models"”.
-
Interpreting black-box models through sufficient input subsets
… the field a reputation of producing opaque, "black-box" models. While deep neural networks are often able to achieve superior predictive accuracy over traditional models, the functions and representations they learn are usually highly nonlinear and difficult to interpret. This lack of …
-
Techniques for Interpretability and Transparency of Black-Box Models
… hinders people's ability to inspect these models. Furthermore, legal requirements are being proposed to require a level of model understanding as a prerequisite to the deployment and use. These factors have spurred research that increases the interpretability and transparency of these …
-
System Level Black-Box Models for DC-DC Converters
The aim of this work is to develop a two-port black-box dc-dc converter modeling methodology for system level simulation and analysis. The models do not require any information about the components, structure, or control parameters of the converter. Instead, all the information needed to build the …
-
Natural counterfactual explanations with causal awareness and actionable recourse for black-box models.
… complexity of artificial intelligence (AI) models, particularly black-box systems, poses substantial challenges to transparency, user trust, and actionable recourse, especially in high-stakes decision-making domains. Counterfactual (CF) explanations, which articulate the minimal input …
-
Toward Efficient Automation of Interpretable Machine Learning Boosting
… (NNs) and Support Vector Machines (SVMs), models which are often highly accurate. Despite high accuracy, such models are essentially “black boxes” and therefore are too risky for situations like healthcare where real lives are at stake. In such situations, so called “glass-box” models, such …
-
On the Certification of Deep Learning-based Dynamical System Identification
… While promising advances have been made, these black box models face significant challenges due to their limited interpretability and lack of physical guarantees, raising concerns about their applicability in scenarios where trustworthiness is critical. In this thesis, we developed a …
-
Unravelling black box machine learning methods using biplots
… from older methods such as generalised linear models. However, their use is currently limited because they are seen as “black box” models, which gives predictions without justifications and which are therefore not understood and cannot be trusted. The goal of this dissertation is to expand on …
-
Scalable black-box model explainability through low-dimensional visualizations
… to provide visual intuitive explanations for how black-box models work. The first is a projection pursuit-based method that seeks to provide data-point specific explanations. The second is a generalized additive model approach that seeks to explain the model on a more holistic level, enabling …
-
Toward Designing Active ORR Catalysts via Interpretable and Explainable Machine Learning
… faster with emerging catalysis databases. Black-box models make up a lot of the ML models that are used in the field to predict the properties of catalysts that are important to their performance, such as their adsorption energies to reaction intermediates. However, as these black-box …
-
Efficient supply chain design for highly-perishable foods
… network decisions, without relying on complex, black-box models that require extensive data collection and hidden assumptions? We apply approximation methods to estimate and compare total logistics cost of supply network designs under various business conditions, such as variations in demand, …
-
Trustworthy Soft Sensing in Water Supply Systems using Deep Learning
… accuracy, but they are often criticized as 'black-box' models due to their lack of transparency. This thesis presents a framework for deep learning-based soft sensors that can quantify the robustness of soft sensors by estimating predictive uncertainty and evaluating performance across …
-
Modeling, identification, and application of multilayer polypyrrole conducting polymer actuators
… actuators to develop low-order lumped parameter models of actuator electrical, mechanical, and electromechanical behavior. Experimental data were processed using system identification techniques. Both grey box and black box models were identified. The grey box model consisted of a first order …
-
Data-driven Algorithms for Critical Detection Problems: From Healthcare to Cybersecurity Defenses
… Existing ransomware defenses often rely on black-box models trained on unverified traces, providing limited interpretability. To address the scarcity of reliably labeled training data, we experimentally profile runtime ransomware behaviors of real-world samples and identify core patterns, …
-
Enhancing a Data-Centric Framework for Predictive Maintenance of Wind Turbines
… lack of domain integration, and reliance on black-box models. Zephyr, a data-centric machine learning framework, addresses these challenges by enabling Subject Matter Experts (SMEs) to incorporate their domain knowledge into the prediction process, and to leverage automated tools for …
-
Estimating Uncertainties in the Joint Reaction Forces of Construction Machinery
… case study for both Matlab and ProMechanica models. Thus, after the Collocation Method was validated on the simple case study, the method was applied to the full 980G II wheel loader in the CAD model in ProMechanica. This study developed and implemented an efficient computational method to …
-
Structure of Artificial Neural Networks : Empirical Investigations
… principles to shed light on to the so called ``black-box models''. Our contributions include a formulation of graph-induced neural networks that is used to pose optimisation problems for neural architecture. We analyse structural properties for different neural network objectives such as …
-
Improving Question Answering Systems with Retrieval Augmented Generation
Large language models (LLMs) have been proven to be state-of-the-art solutions for many NLP benchmarks. However, LLMs in real applications face many limitations. Although such models are seen to contain real-world knowledge, it is kept implicitly in their parameters that cannot be revised and …
-
Interactive Visual Self-service Data Classification Approach to Democratize Machine Learning
<p>Machine learning algorithms often produce models considered as complex black-box models by both end users and developers. Such algorithms fail to explain the model in terms of the domain they are designed for. The proposed Iterative Visual Logical Classifier (IVLC) is an interpretable machine …
-
Characterization of Cooled Turbine Efficiency for Off-Design Performance Models
… on how they are represented in performance models. The challenge is especially present in “black-box” approaches, where only inlet and outlet conditions are known and engineers must decide whether to introduce cooling flows upstream (if performing useful work) or downstream (if not). This …
-
Co-Design of Resource Limited Genetic Networks Tuning System Parameters to Satisfy Specifications
… parts of the systems can be encapsulated into black box models characterized only by its input to output behavior, which eliminates the need to consider the complex dynamics inside the black box. Moreover, this process can be done iteratively, allowing the design of highly complex systems, such …
Page 1 of 3