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 8 of 8 for “"Model Explainability"”.
-
Scalable black-box model explainability through low-dimensional visualizations
… 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 users to …
-
Appley: Approximate Shapley Values for Model Explainability in Linear Time
<p>We have seen complex deep learning models outperforming human benchmarks in many areas (e.g. computer vision, natural language processing). Clever architectures and higher model complexity are two of the major drivers of such outstanding performances. Higher model complexity generally makes the …
-
Enhancing detection of cervical cancer through deep learning: a comparative study of histological image-based algorithms
… this thesis, I investigate the application of DL models—ResNet50, SqueezeNet, EfficientNet, and a Visual Prompting Model—for classifying cervical cells using histopathological images. I conduct a comparative analysis to evaluate these models based on accuracy, sensitivity, specificity, and …
-
MRI microstructure and morphology enable machine learning-based prediction of freezing of gait in Parkinson’s disease.
… Progression Marker Initiative. The trained model demonstrated high accuracy (AUC=0.91, Sensitivity=0.94, Specificity=0.80) on unseen data. Model explainability analysis revealed key microstructural and morphometric features within limbic, executive, and visual networks, supporting the idea …
-
Pairwise Matching of Intermediate Representations for Fine-grained Explainability
… often subtle and highly localized, and existing explainability techniques for deep learning models are often too diffuse to provide useful and interpretable explanations. We propose a new explainability method (PAIR-X) that leverages both intermediate model activations and backpropagated …
-
Imaging Based Models to Improve Lung Cancer Diagnosis
… cancer, all while factoring in the importance of model explainability in clinical settings. Recent advances in deep learning have led to increased applications of machine learning to medical imaging. In this work, we seek to better understand lung cancer through the computer vision tasks of risk …
-
A Unified Theory of Representation Learning: How Hidden Relationships Power Algorithms that can Learn without Labels
… structure of the natural world by connecting model explainability, cooperative game theory, and deep feature relationships. The second mathematical theory will show that relationships between representations can be used to unify over 20 common machine learning algorithms spanning 100 years of …
-
Robustness in sum-product networks: from measurement to ensembles
… of a classification through perturbing model weights using Credal Sum-Product Networks and creating a metric in the form of robustness to represent this is presented and demonstrated empirically to be of use in this context. We propose a practical use for this tool as a key component of …