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 16 of 16 for “"Post-hoc Explanation"”.

  1. Exploring neural network interpretability in visual understanding

    … NN interpretability in diverse visual tasks from post-hoc explanation and intrinsic interpretability perspectives. Convolutional neural networks (CNNs) have outperformed humans in image classification. However, the logic of network decisions remains a puzzle. As such, we propose concept-harmonized …

    ubc Repository record for Exploring neural network interpretability in visual understanding (opens in a new tab) Download PDF for Exploring neural network interpretability in visual understanding (opens in a new tab)

  2. POWER AND COHERENCE MATTERS: DOES PERCEIVED GROUP ORGANIZATION INCREASE ATHEIST PREJUDICE?

    … decreases prejudice towards atheists. One post-hoc explanation provided for this difference is that since atheists are easily concealable and unorganized as a group, their greater prevalence may not be perceived as a threat. In the present thesis, I 1) attempted to replicate the existing …

    csusb Repository record for POWER AND COHERENCE MATTERS: DOES PERCEIVED GROUP ORGANIZATION INCREASE ATHEIST PREJUDICE? (opens in a new tab)

  3. The relationship between extent of aftereffect and speed of a rotated spiral

    … or the function of speed on the aftereffect. A post hoc explanation was offered to explain the effect of speed on spiral aftermovement by an extension of the statistical summation theory. The following prediction was based on pilot data with the intent to determine if speed was a stable general …

    bu Repository record for The relationship between extent of aftereffect and speed of a rotated spiral (opens in a new tab)

  4. Transformation-invariance properties of Grad-CAM in Convolutional Neural Networks

    … Class Activation Mapping (Grad-CAM) is a post-hoc explanation technique that generates visual heatmaps to highlight the class-relevant regions in an input image. However, in real-world scenarios, input images often undergo transformations such as rotation, zoom, and shifts along the …

    uoit Repository record for Transformation-invariance properties of Grad-CAM in Convolutional Neural Networks (opens in a new tab)

  5. Towards Reliable and Trustworthy Deep Learning through Explainability and Interpretability

    … of deep learning models. First, we develop new post-hoc explanation methods that improve feature attribution and concept-based explanations. These methods provide faithful decision cues by modeling meaningful feature interactions and extracting faithful coherent concepts, enabling more reliable …

    rit Repository record for Towards Reliable and Trustworthy Deep Learning through Explainability and Interpretability (opens in a new tab)

  6. Unifying Explainability and Machine Learning: Towards Trustworthy and Plausible Explanations without Post-hoc Manipulations

    … and enhance model interpretability, ensuring explanations are both faithful (accurate to the model’s reasoning) and plausible (intelligible to human users). A key challenge in XAI is the unreliability of post-hoc explanation methods. To address this, we propose (1) quantitative evaluation …

    rowan Repository record for Unifying Explainability and Machine Learning: Towards Trustworthy and Plausible Explanations without Post-hoc Manipulations (opens in a new tab)

  7. Improving the interpretability of machine learning approaches with user-generated data

    … of the model overcomes the limitations of common post-hoc explanation techniques. Furthermore, since the resulting explanations are faithful to the model reasoning, the results can also be used for model debugging and hyperparameter tuning.

    birmingham Download PDF for Improving the interpretability of machine learning approaches with user-generated data (opens in a new tab)

  8. Model Explainability: From Post-hoc to Self-explainable

    … through three complementary approaches: improved post-hoc explanation methods, internal mechanism understanding, and inherently interpretable architectures. First, we tackle the challenge of explaining video understanding models by proposing Frequency-based Extremal Perturbation (F-EP), which …

    rit Repository record for Model Explainability: From Post-hoc to Self-explainable (opens in a new tab)

  9. Towards Explainable Time Series: An Exploration Of Post-hoc Local Explanations From A Multi-disciplinary Perspective

    … the Explainable AI landscape, post-hoc local explanations, which help users understand why a black-box returned a particular output for a particular input, have become the most widely applied tool. Despite their success, post-hoc explanations are still in their infancy and …

    bristol Repository record for Towards Explainable Time Series: An Exploration Of Post-hoc Local Explanations From A Multi-disciplinary Perspective (opens in a new tab) Download PDF for Towards Explainable Time Series: An Exploration Of Post-hoc Local Explanations From A Multi-disciplinary Perspective (opens in a new tab)

  10. Physical Side-Channel Vulnerability Assessment of Implementations of Cryptographic Algorithms

    … features from the NN models using gradient-based post hoc explanation methods to the ones obtained by traditional points of interest (PoI) selection methods. Third, we performed a power side-channel vulnerability assessment of a parallel hardware implementation of one of the finalists of the NIST …

    gatech Repository record for Physical Side-Channel Vulnerability Assessment of Implementations of Cryptographic Algorithms (opens in a new tab)

  11. The impact of cultural values on email acceptance : evidence from the PRC

    … typology and to remedy the inadequacy of post hoc explanation in conventional IS cultural studies. Instead of using the scores of national culture proposed by Hofstede’s cultural study in 1980, this study measures cultural values in terms of personal traits to reflect the changes in and …

    lingnan Repository record for The impact of cultural values on email acceptance : evidence from the PRC (opens in a new tab)

  12. Hipiess: A Framework for Artificial Intelligence and Machine Learning in Clinical Informatics

    … (XAI) methods such as feature attribution and post-hoc explanation techniques offer partial insight into model behavior, they often fail to align with clinical reasoning, are not actionable, and are rarely integrated into clinical workflows. Finally, deployment systems such as clinical decision …

    gatech Repository record for Hipiess: A Framework for Artificial Intelligence and Machine Learning in Clinical Informatics (opens in a new tab)

  13. Causal and system-theoretic approaches to interpretable machine learning

    … addresses these challenges by exploring both post-hoc explanation methods and augmentation based strategies for increasing interpretability. We begin by examining existing explainable AI (XAI) methods, which aim to attribute a model’s output to its input features. Focusing on the widely used …

    umn Repository record for Causal and system-theoretic approaches to interpretable machine learning (opens in a new tab)

  14. Algorithmic Decision-Making Facilities: Perception and Design of Explainable AI-based Decision Support Systems

    … of AI-based DSSs. This yields a plethora of explanation techniques, creating an XAI jungle from which end-users must choose. In turn, these techniques are preliminarily engineered by developers for developers without ensuring an actual end-user fit. Thus, it renders unknown how an end-user’s …

    wurz-thes Repository record for Algorithmic Decision-Making Facilities: Perception and Design of Explainable AI-based Decision Support Systems (opens in a new tab)

  15. New and Advanced Explainable Artificial Intelligence Approaches for Managing Project Risks

    … among risk factors, often producing fragmented explanations that overlook the structural dependencies underlying overall project vulnerability. In PRM, this limitation is particularly critical as risks are inherently interdependent, and disturbances in one aspect can propagate across multiple …

    unsw Repository record for New and Advanced Explainable Artificial Intelligence Approaches for Managing Project Risks (opens in a new tab)

  16. PROBABILISTIC MODEL CHECKING WITH MARKOV MODELS SEMANTICS: NEW DEVELOPMENTS AND APPLICATIONS

    … our focus to a specific XAI framework, i.e., post-hoc explanation methods based on surrogate models. More specifically, we pro- pose a logic and related model-checking procedures for specifying and checking relevant reliability properties of XAI-explanations for opaque ML systems provided via …

    milano Repository record for PROBABILISTIC MODEL CHECKING WITH MARKOV MODELS SEMANTICS: NEW DEVELOPMENTS AND APPLICATIONS (opens in a new tab)