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 22 for “"Model Interpretation"”.
-
Contributions to Structured Variable Selection Towards Enhancing Model Interpretation and Computation Efficiency
… selection of variables should facilitate the model interpretation and computation efficiency. It is thus important to incorporate domain knowledge of underlying data generation mechanism to select key variables for improving the model performance. However, general variable selection …
-
Interpretations of Machine Learning and Their Application to Therapeutic Design
… for interpreting black-box machine learning (ML) models, discover overinterpretation as a failure mode of deep neural networks, and discuss how ML methods can be applied for therapeutic design, including a pan-variant COVID-19 vaccine. While ML models are widely deployed and often attain superior …
-
The influence of structure formation on the evolution of the universe
… of determining key parameters of a cosmological model to percent level and beyond. For this to be effective, the theoretical model must be understood to at least the same level of precision. A range of subtle physical spacetime effcts remain to be explored theoretically, for example, the effect …
-
Automated Interpretation of Machine Learning Models
As machine learning (ML) models are increasingly deployed in production, there’s a pressing need to ensure their reliability through auditing, debugging, and testing. Interpretability, the subfield that studies how ML models make decisions, aspires to meet this need but traditionally relies on …
-
Analysing Student Code Submissions Using Program Analysis Techniques and Large Language Models
… from static analysis tools, while large language models provide accessible explanations but lack formal guarantees. This thesis investigates when static analysis grounding—that is, providing the model with structured tool output (such as compiler warnings or type errors) to anchor its …
-
The introduction and application of recursive partitioning methods in organizational science
… field of organizational science for predictive modeling. Despite its pervasive use, the classical regression model falls short in several aspects, including the lack of flexibility in handling complex nonlinear relationships and the strict assumptions imposed by parametric approaches. To …
-
A Study of the Λ(1405) in Lattice QCD
… to reconcile this low mass with the quark model interpretation for this state, and lattice QCD studies have consistently failed to reproduce it. In this work, we use the PACS-CS (2+1)-flavour full-QCD ensembles together with a variational analysis using source and sink smearing in an …
-
Comparison of Logistic Regression and Classification Trees to Forecast Short Term Defaults on Repeat Consumer Loans
… (algorithm machine learning basis) and model interpretation. Past research has found classification trees to perform marginally better than logistic regression with respect to predictiveness and robustness when modelling short term consumer credit default outcomes related to previously …
-
Bayesian Analysis of Latent Threshold Dynamic Models
Time series modeling faces increasingly high-dimensional problems in many scientific areas. Lack of relevant, data-based constraints typically leads to increased uncer-tainty in estimation and degradation of predictive performance. This dissertation addresses these general questions with a new and …
-
Why Are Some Watersheds More Sediment-Productive Than Others? An Explainable AI Approach
… Here, we develop a data-driven framework to model SDR and SY across the contiguous United States (CONUS) by integrating high-frequency aquatic sensing, sediment load estimation, and explainable machine learning. SY and SDR were quantified at 134 U.S. Geological Survey (USGS) stations and …
-
Novel Algorithms for Understanding Online Reviews
… non-negative matrix factorization model to deal with this problem. It effectively incorporates the word-context semantic correlations into the model, where the semantic relationships between the words and their contexts are learned from the skip-gram view of a corpus. We conduct …
-
Evaluation, Interpretation, and Maintenance of Machine Learning Models for IT Operations
… of large-scale systems and machine learning models to assist in managing system operations. While prior studies focus on innovative modeling techniques to improve the performance of AIOps models, how to smoothly transition AIOps solutions from development to production remains an …
-
A Composite Syntactic-Semantic Interpretable Text Entailment Approach Exploring Commonsense Knowledge Graphs
… towards Explainable AI, allowing the inference model interpretation, making the semantic reasoning process explicit and understandable.
-
A systemic exploration of the external risk factors impacting SMEs survival in South Africa
… interrelations using Interpretive Structural Modelling. This objective was addressed through the following research questions. a) What are the key risk factors affecting the survival of SMEs in South Africa? b) What is the relationship between the identified key risk factors? c) What is the …
-
Risk-based Renewal Prioritization Models (RPM) for Potable Water Pipeline Infrastructure Systems
… risk with decision criteria, ad hoc selection of modeling algorithms without strategic foresight, and limited, often internal-only, real-world validation. This dissertation addresses these gaps by developing and testing an AI-enabled framework for risk-based renewal prioritization of water …
-
SPATIALLY EXPLICIT MODEL OF AREAS BETWEEN SUITABLE BLACK BEAR HABITAT IN EAST TEXAS AND BLACK BEAR POPULATIONS IN LOUISIANA, ARKANSAS, AND OKLAHOMA
… utilized Maxent, a machine learning software, to model habitat suitability in this region. I collected known black bear presence locations (n=18,241) from state agencies in Louisiana, Oklahoma, Arkansas and east Texas and filtered them to reduce spatial autocorrelation (n=664). I also collected …
-
Towards the Development of Cost-Effective Decentralized Applications: An Investigation of Transaction Processing Times on the Ethereum Blockchain Platform
… do not disclose any information regarding their models, particularly information about the used and most important features in the predictions of these models. These issues make it difficult for ÐApp developers to fully trust the predictions generated by such platforms, and also prevents them …
-
HybridMDSD: Multi-Domain Engineering with Model-Driven Software Development using Ontological Foundations
… To reduce technical complexity, the paradigm of Model-Driven Software Development (MDSD) facilitates the abstract specification of software based on modeling languages. Corresponding models are used to generate actual programming code without the need for creating manually written, error-prone …
-
Interpretation, Identification and Reuse of Models. Theory and algorithms with applications in predictive toxicology.
… developing methodologies that enable existing models to be effectively reused. Results of this thesis are presented in the framework of Quantitative Structural-Activity Relationship (QSAR) models, but their application is much more general. QSAR models relate chemical structures with their …
-
Interpretation, Identification and Reuse of Models. Theory and algorithms with applications in predictive toxicology.
… developing methodologies that enable existing models to be effectively reused. Results of this thesis are presented in the framework of Quantitative Structural-Activity Relationship (QSAR) models, but their application is much more general. QSAR models relate chemical structures with their …
Page 1 of 2