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 35 for “"Counterfactual Explanations"”.

  1. Generation and evaluation of semantic counterfactual explanations

    … of complex models. This dissertation focuses on counterfactual explanations, which determine the minimal input modifications required to alter an AI model’s prediction. A domain-agnostic, black-box framework for counterfactual generation is introduced, applicable across multiple data modalities, …

    greece Repository record for Generation and evaluation of semantic counterfactual explanations (opens in a new tab)

  2. On evaluating counterfactual explanations for Machine Learning Models

    … Learning – ML) μέσω αντιπαραθετικών εξηγήσεων (counterfactual explanations – CF), οι οποίες περιλαμβάνουν την πραγματοποίηση μικρών μεταβολών στα δεδομένα εισόδου προκειμένου να διερευνηθούν εναλλακτικά αποτελέσματα. Αναγνωρίζοντας τη διαρκώς αυξανόμενη σημασία της αξιολόγησης της απόδοσης …

    athens Repository record for On evaluating counterfactual explanations for Machine Learning Models (opens in a new tab)

  3. Responsible decision-making in trustworthy human-AI interaction: linking counterfactual explanations and regret

    … the somatic marker hypothesis driven by the counterfactual component of the anticipated regret could serve as a recommendation norm for preventing unspecified errors before they occur. Chapter 1 introduces the dissertation topic and justifies the motivations for conducting it. Chapter 2 …

    valladolid Repository record for Responsible decision-making in trustworthy human-AI interaction: linking counterfactual explanations and regret (opens in a new tab)

  4. Causality concepts in machine learning: heterogeneous treatment effect estimation with machine learning & model interpretation with counterfactual and semi-factual explanations

    … concepts to interpret machine learning models: counterfactual explanations and semi-factual explanations. Counterfactual explanations describe minimal changes in a few features required for changing a prediction, while semi-factual explanations describe maximal changes in a few features required …

    lmu-germany Repository record for Causality concepts in machine learning: heterogeneous treatment effect estimation with machine learning & model interpretation with counterfactual and semi-factual explanations (opens in a new tab)

  5. Multi-objective approaches towards trustworthy machine learning

    … data changes over time, and methods to provide explanations for model decisions need to operate efficiently and in real-time. In this thesis, we address these challenges by developing frameworks that can account for more than one characteristic of responsible artificial intelligence. First, we …

    texas Repository record for Multi-objective approaches towards trustworthy machine learning (opens in a new tab)

  6. What does explainable AI explain?

    … aspects beyond predictive performance through explanations. However, the field is still in its infancy, as fundamental questions such as “What are explanations?”, “What constitutes a good explanation?”, or “How relate explanation and understanding?” remain open. In this dissertation, I combine …

    lmu-germany Repository record for What does explainable AI explain? (opens in a new tab)

  7. Supporting Human Performance with Post-hoc Explanations in Automated Decision Assistance

    … promote appropriate reliance behaviors. Post-hoc explanations have emerged as a strategy to support appropriate reliance on automated decision aids based on machine learning. However, existing methods to generate post-hoc explanations often fail to demonstrate systematic effectiveness in aiding …

    toronto-retro Repository record for Supporting Human Performance with Post-hoc Explanations in Automated Decision Assistance (opens in a new tab)

  8. Personalized Algorithmic Recourse: Towards a human-centric approach for algorithmic contestability

    … individuals to challenge, appeal, or seek explanations for AI-driven decisions. Indeed, while legal frameworks, such as the EU AI Act, conceptualize contestability, they fail to describe technically or scientifically actionable methodologies for effective implementation. In machine …

    trento Repository record for Personalized Algorithmic Recourse: Towards a human-centric approach for algorithmic contestability (opens in a new tab)

  9. PRINCIPLED ANALYSIS OF MODEL EXPLANATIONS

    … While user studies are ideal for evaluating explanations in particular contexts, they are costly and impractical at scale. This thesis adopts a complementary approach by focusing on high-level properties and axioms that explanations should satisfy. First, we employ axiomatic characterization …

    nus Repository record for PRINCIPLED ANALYSIS OF MODEL EXPLANATIONS (opens in a new tab) Download file for PRINCIPLED ANALYSIS OF MODEL EXPLANATIONS (opens in a new tab)

  10. Explaining Expert Search and Team Formation Systems with ExES

    … systems. Our system leverages saliency and counterfactual methods from the field of explainable artificial intelligence (XAI). ExES enables users to understand why individuals were or were not included in the query results and what individuals could do, in terms of perturbing skills or …

    waterloo Repository record for Explaining Expert Search and Team Formation Systems with ExES (opens in a new tab)

  11. Counterfactuals for Interpretable Machine Learning: Model Reasoning from “What” to “How”

    … in reasoning decisions and understanding "how". Counterfactual Explanation, serving as one of the emerging types of ML interpretations, has raised the attention from both researchers and practitioners in recent years. Counterfactual explanation is essentially a series of hypothetical data …

    rice Repository record for Counterfactuals for Interpretable Machine Learning: Model Reasoning from “What” to “How” (opens in a new tab)

  12. Algorithmic approaches for efficiency and explainability in learning problems

    … to noisy and incomplete data. (2) For global counterfactual explanations, the problem is formulated as a multi-objective optimization balancing interpretability, cost, and effectiveness. Its computational hardness is formally established, and efficient clustering-based algorithms are …

    greece Repository record for Algorithmic approaches for efficiency and explainability in learning problems (opens in a new tab)

  13. Novel mathematical optimization Models for Group counterfactual Analysis

    … Such modified solutions, the so-called counterfactual explanations, are addressed in this thesis. This dissertation is devoted to extending the study of counterfactual analysis across different dimensions. Specially, we delve into group analysis, where, instead of considering a single …

    sevilla Repository record for Novel mathematical optimization Models for Group counterfactual Analysis (opens in a new tab)

Page 1 of 2