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 194 for “"Model Interpretability"”.
-
Model Interpretability for Natural Language Processing Applications
This thesis focuses on model interpretability, an area concerned with under- standing model predictions in Natural Language Processing (NLP) tasks. The increase in adoption of opaque models, such as BERT, leads to an increasing need for explaining their predictions. This is typically performed by …
-
Wrapper boxes for increasing model interpretability via example-based explanations
We propose wrapper boxes to provide interpretability in deep learning that is model, training, and dataset-agnostic. The prediction model is trained as usual on some dataset(s), typically optimizing some predetermined loss function. At inference time, the prediction model is augmented by a simpler …
-
Human-in-the-loop Machine Learning System via Model Interpretability
<p>The interpretability of a machine learning system is crucial in situations where it involves human-model interaction or affects the well-being of society. By making the decision process understandable to humans, interpretability makes it easier to troubleshoot, acquire knowledge from, and …
-
NEURAL NETWORK MODEL INTERPRETABILITY FOR COMPUTER NETWORK OPERATIONS AND DEFENSE
… test deterministic and Bayesian neural network models as classifiers to discriminate benign traffic from traffic that should be blocked by a firewall network security device. Using Bayesian methods for neural networks, we demonstrate ways to capture and visualize uncertainty and confidence …
-
SEARCHING FOR NOOKS AND CRANNIES: GEOMETRIC AND MECHANISTIC PERSPECTIVES ON TRANSFORMER LANGUAGE MODEL INTERPRETABILITY
Large language models (LLMs) have demonstrated remarkable linguistic capabilities, but the internal mechanisms driving their performance and behavior remain poorly understood. This dissertation investigates the interpretability of transformer-based language models from two complementary …
-
SEARCHING FOR NOOKS AND CRANNIES: GEOMETRIC AND MECHANISTIC PERSPECTIVES ON TRANSFORMER LANGUAGE MODEL INTERPRETABILITY
Large language models (LLMs) have demonstrated remarkable linguistic capabilities, but the internal mechanisms driving their performance and behavior remain poorly understood. This dissertation investigates the interpretability of transformer-based language models from two complementary …
-
Pattern Recognition and Quantifying Associations Within Entities of Data Driven Systems for Improving Model Interpretability
… function, at the cost of compromising the interpretability of the models. A new branch of machine learning focuses on model interpretability by explaining the models in various ways. The foundation of model interpretability is built on extracting patterns from the behavior of the models and …
-
Forecasting Pharmaceutical Expenditure at Sjúkratryggingar Íslands : A Comparative Machine Learning Analysis Emphasizing Model Interpretability and Practical Deployment
… SÍ can reliably apply in practice, weighing interpretability alongside accuracy. Methods: Using 84 months of cleaned monthly claims data (2019–2025), Linear Regression, Prophet, XGBoost and Random Forest were used to forecast total pharmaceutical expenditure. The models were backtested by …
-
Early ICU Physiological Subtyping From Time-Series Data: A Comparative Study of Feature Complexity, Predictive Performance, and Model Interpretability
… to K-Means (K = 3) and Bayesian Gaussian Mixture Model (BGMM) clustering algorithms to discover the underlying patient subtypes. Supervised learning is employed using Logistic Regression and XGBoost classifiers to predict patient in-hospital mortality risk. Study 1 achieves strong performance with …
-
Explainable deep learning for image understanding
… by attributes, pruning techniques to enhance model interpretability, and a framework for 3D editing informed by visual explanations. These advancements boost model trust across diverse applications.
-
Automated Valuation Model for Residential Properties using Machine Learning Approaches: A Case Study of Greater Sydney, Australia
… for various stakeholders. Automated Valuation Models (AVMs), which offer more consistency and objectivity than manual valuations, are increasingly being adopted for housing valuation. In particular, AVMs based on machine learning (ML) algorithms have gained attention for their superior accuracy …
-
Kernel Methods and Measures for Classification with Transparency, Interpretability and Accuracy in Health Care
… understanding and transparency for kernel/model selection with atomic data types. The kernels and framework necessarily co-exist. The secondary goal of this thesis is to quantitatively measure model interpretability for kernel/model selection and identify the types of interpretable …
-
Interpretable Machine Learning (IML) Methods: Classification and Solutions for Transparent Models
… of machine learning (ML), focusing on enhancing model interpretability called interpretable machine learning (IML) techniques. The initial chapter provides a comprehensive overview of various ML models, including supervised, unsupervised, reinforcement, and hybrid learning methods, emphasizing …
-
Expanding the capabilities of Bayesian regression with interactions and smooth effects
… and Smooth Effects) method of regression modelling was designed to improve upon other flexible regression schemes in the areas of model interpretability and ease of implementation. B-WISE models have been shown to have good predictive performance, and performance can be even further …
-
Novel Techniques Using Graph Neural Networks (GNNS) for Anomaly Detection
… accurately. Using Fisher information improves model interpretability while ChebNet modules help leverage spectral properties.
-
Dirbtinis intelektas kardiologijoje-aritmologijoje /
… monitoring through wearable devices. AI models have demonstrated accuracy comparable to or exceeding that of human experts in many tasks, such as detecting atrial fibrillation and other cardiac abnormalities. The review also explores AI's potential in drug management, electrophysiology …
-
Beta-Binomial Kriging: A New Approach to Modeling Spatially Correlated Proportions
… estimates and predictions, at the cost of model interpretability and simplicity. This dissertation will present a new approach to modeling spatially correlated binomial observations: beta-binomial kriging. The model proposed here is a modified form of spatial kriging which assumes the data …
-
iVLAIR - Interface Design and Prototype for Interactive Visualization-Mediated Supervised Classification
… writing code. However, for most machine learning models, it is difficult to understand how they arrive at a particular result. This challenge has triggered a lot of research on interpretable ML methods. However, these methods also require the user to learn how to code and implement them. In this …
-
Computational causal discovery from observational data and application in bioinformatics
… objective function in terms of better model interpretability and more effective sample utilization. First, we propose a novel constraint-based method which utilizes both prior knowledge and observational data to learn more reliable and accurate causal structures. The method is …
-
A novel spatiotemporal framework for efficient traffic prediction and visualization
… Linear Regression-based traffic prediction model, and an interactive map-based traffic simulator to visualize the results. To collect traffic data, we have developed an open-source web-based data scraper tool to extract and export publicly available traffic data from the Google Maps web …
Page 1 of 10