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 33 for “"Counterfactual Reasoning"”.

  1. The theory of Boolean counterfactual reasoning

    Ursache und Wirkung bilden eine Grundlage dafür, wie Menschen ihre Umwelt wahrnehmen. Wir erklären unsere Umwelt, indem wir Beobachtungen als Wirkung anderer, selbsterklärender Beobachtungen beschreiben. Angenommen, ein Haus brennt nach einem Blitzschlag. In diesem Fall können wir den Blitz als …

    lmu-germany Repository record for The theory of Boolean counterfactual reasoning (opens in a new tab)

  2. The Bidirectional Relation Between Counterfactual Reasoning and Morality in Development

    Counterfactual reasoning involves thinking about how past could have been better or worse (e.g., "If only I had booked a taxi, I would have made it to the airport on time."). Substantial evidence has revealed that imagining alternatives to reality influences adults' moral judgments, emotions and …

    kent Download PDF for The Bidirectional Relation Between Counterfactual Reasoning and Morality in Development (opens in a new tab)

  3. Counterfactual Reasoning and Uncertainty Quantification for AI-Assisted Decision Making

    … leverage the interaction with the expert through counterfactual reasoning and uncertainty quantification. It proposes decision support systems for three distinct decision-making contexts described below, where each one is based on a novel methodological approach and is evaluated with experiments …

    ethz Repository record for Counterfactual Reasoning and Uncertainty Quantification for AI-Assisted Decision Making (opens in a new tab)

  4. The effects of neurological damage on counterfactual thinking, regret, and decision making

    In 5 experiments neurologically damaged patients’ counterfactual reasoning, decision making (DM) and experience of counterfactually mediated emotions (CME) was explored. 17 patients, with varying lesion sites resulting from a stroke, (7 female) aged between 31 and 84 (M=64.5 years) and 17 controls …

    birmingham Download PDF for The effects of neurological damage on counterfactual thinking, regret, and decision making (opens in a new tab)

  5. Exploiting Causal Reasoning to Improve the Quantitative Risk Assessment of Engineering Systems Through Interventions and Counterfactuals

    … analysts’ knowledge of a system and enable reasoning under uncertainty. Currently, the use of BNs for risk-informed decisions is based solely on associative reasoning, answering questions of the form "If we observe X=x, how likely is it to observe Y=y?” However, risk management in the …

    maryland Repository record for Exploiting Causal Reasoning to Improve the Quantitative Risk Assessment of Engineering Systems Through Interventions and Counterfactuals (opens in a new tab)

  6. Counterfactual Evaluation And Learning From Logged User Feedback

    … -- They open further avenues for research in Counterfactual Evaluation and Learning to ensure machine learned components interact reliably with users and with each other. This thesis explores two fundamental tasks — evaluation and training of interactive systems. Solving evaluation and …

    cornell Repository record for Counterfactual Evaluation And Learning From Logged User Feedback (opens in a new tab)

  7. Constructing Causal Knowledge Representation with the Common Model of Cognition

    … allowed for a new approach to represent causal reasoning. By implementing relation types analogous to a do-operator (Pearl, 2010, 2013, 2021) and structuring symbolic representation of knowledge in the Python ACT-R declarative memory module according to the Ladder of Causation (Pearl & …

    carleton Repository record for Constructing Causal Knowledge Representation with the Common Model of Cognition (opens in a new tab)

  8. Interpretable Machine Learning: Explaining Models, Datasets and Expert Behaviors

    … interpreting any black-box models decisions by counterfactual reasoning; we find it finds more relevant and important features than the baselines. Then I describe the remaining three works on Generalized Additive Models (GAMs) - an inherently interpretable model class. I first compare different …

    toronto-retro Repository record for Interpretable Machine Learning: Explaining Models, Datasets and Expert Behaviors (opens in a new tab)

  9. Causal Neuro-Symbolic Artificial Intelligence: Synergy Between Neuro-Symbolic and Causal Artificial Intelligence

    Understanding and reasoning about cause and effect is innate to human cognition. In everyday life, humans continuously engage in causal reasoning and hypothetical retrospection to make decisions, plan actions, and interpret events. This cognitive ability allows us to ask questions such as: “What …

    south-carolina Repository record for Causal Neuro-Symbolic Artificial Intelligence: Synergy Between Neuro-Symbolic and Causal Artificial Intelligence (opens in a new tab)

  10. The Effects of Counterfactual Priming on Belief in Fake News

    … the negative effects of confirmation bias; counterfactual reasoning is one that has demonstrated success. In the current study, participants were assigned to either a counterfactual priming scenario or a non-counterfactual scenario, before assessing the accuracy of a series of images that …

    shu-thes Repository record for The Effects of Counterfactual Priming on Belief in Fake News (opens in a new tab)

  11. Comprehending counterfactuals

    Counterfactual reasoning, an understanding of events that are counter to reality, or false, is an essential ingredient of our everyday cognition. Counterfactual situations are frequently depicted through language, yet surprisingly little is known of how they are processed during reading or …

    glasgow Download PDF for Comprehending counterfactuals (opens in a new tab)

  12. Constrained, Causal, and Knowledge-Grounded Reasoning for Neural Language Generation

    … thesis aims to establish a connection between reasoning and language generation. Today's language models (LMs, such as GPT-3), despite producing human-like fluent text, essentially act like "a mouth without a brain" -- They generate without grounding on the world knowledge, and lack the ability …

    washington Repository record for Constrained, Causal, and Knowledge-Grounded Reasoning for Neural Language Generation (opens in a new tab)

  13. Causal Graphical Models in AI Reasoning & Expert Decision-Making

    … cause-effect relationships, supporting causal reasoning in novel and uncertain environments. Probability theory and causal inference provide principled frameworks that further aid humanity in reasoning about causal mechanisms with limited prior knowledge. As causal reasoning is a hallmark of …

    cornell Repository record for Causal Graphical Models in AI Reasoning & Expert Decision-Making (opens in a new tab)

  14. Prediction, Interpretation and Counterfactual Generation for Acute Care Applications

    … biomedical domain knowledge. Third, we generate counterfactual patient trajectories to explore how changes in treatments or physiological states may have influenced outcomes. Applied on real-world intensive care datasets, the framework demonstrate strong predictive performance, interpretable …

    arizona-thes Repository record for Prediction, Interpretation and Counterfactual Generation for Acute Care Applications (opens in a new tab)

  15. Deep learning for electronic health records: risk prediction, explainability, and uncertainty

    … looked into explanations in risk association and counterfactual reasoning. Uncertainty estimation was qualitatively investigated using probabilistic modelling techniques. Our analyses relied on Clinical Practice Research Datalink, which contains anonymised EHR collected from primary care, …

    oxford Repository record for Deep learning for electronic health records: risk prediction, explainability, and uncertainty (opens in a new tab)

  16. Stop the press : are the news media taking over foreign policy?

    … effect and show them to be lacking. Then, using counterfactual reasoning, the case of Somalia will be reviewed in an attempt to ascertain if the CNN effect operated in that case. The discussion will show that, despite .the fact that Somalia is most often cited as the crisis that best demonstrates …

    ubc Repository record for Stop the press : are the news media taking over foreign policy? (opens in a new tab) Download PDF for Stop the press : are the news media taking over foreign policy? (opens in a new tab)

  17. Unbiased Learning-to-Rank from Logged Implicit Feedback

    … end, we develop a theoretical framework based on counterfactual reasoning that systematically deals with the various forms of position bias inherent in user behavior, and demonstrate its effectiveness in several real-world settings including Gmail and Arxiv search. While the framework can be …

    cornell Repository record for Unbiased Learning-to-Rank from Logged Implicit Feedback (opens in a new tab)

  18. Causal artificial intelligence for robust robot reasoning under uncertainty

    … a conceptual framework for <em>Robot Causal Reasoning</em> that integrates structural causal models, probabilistic planning, and (deep and classical) generative world modelling to enhance robot perception, inference, decision-making, and explanation. Across six research questions, the work …

    oxford Repository record for Causal artificial intelligence for robust robot reasoning under uncertainty (opens in a new tab)

  19. Graph-Based Retrieval-Augmented Generation for Cancer Clinical Decision Support: Explainable Paths with Cross-Patient Cohort Reasoning

    … as flat text chunks, which weakens relational reasoning across patients and limits auditable evidence tracing. This thesis presents GRAG-Cancer, a graph-augmented retrieval framework that integrates dense retrieval with a patient-centric clinical knowledge graph for breast cancer decision …

    ut-knoxville Repository record for Graph-Based Retrieval-Augmented Generation for Cancer Clinical Decision Support: Explainable Paths with Cross-Patient Cohort Reasoning (opens in a new tab)

  20. Causal Preference Inference in Reinforcement Learning-Based Recommender System

    … well to unseen scenarios. To address this, counterfactual reasoning is leveraged to generate counterfactual user interactions, augmenting training data and improving the agent’s ability to model user behavior more accurately. Second, the complexity of state representations in RLRS poses a …

    unsw Repository record for Causal Preference Inference in Reinforcement Learning-Based Recommender System (opens in a new tab)

Page 1 of 2