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 65 for “"Shapley values"”.

  1. Appley: Approximate Shapley Values for Model Explainability in Linear Time

    … A coalition game theoretic approach called Shapley Value provides a fair way to tackle the challenge. However, the growth of computation time of the exact Shapley Values is exponential in the number of variables. Hence, it is common to use approximations as opposed to the exact Shapley …

    kennesaw Repository record for Appley: Approximate Shapley Values for Model Explainability in Linear Time (opens in a new tab)

  2. Shapley Values and Machine Learning to Characterize Metamaterials for Seismic Application

    … such a correlation, in this thesis, we will use Shapley values, a technique from the cooperative game theory. In addition, we will develop machine learning models that can predict the QoIs for a set of input parameters.

    houston Repository record for Shapley Values and Machine Learning to Characterize Metamaterials for Seismic Application (opens in a new tab)

  3. Understanding Facets of Instance Level Effects in Explainable Artificial Intelligence Tasks using Shapley Values

    … data instances and the model, in the context of Shapley Values. In particular, to build upon existing works to provide methods that offer justification of what made each data instance important and to use this information to generate actionable feedback to an ML workflow. This information can be …

    anu Repository record for Understanding Facets of Instance Level Effects in Explainable Artificial Intelligence Tasks using Shapley Values (opens in a new tab)

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

    … input and output variables. We next consider Shapley values, another prominent XAI method that has demonstrated the ability to generate coherent explanations across different types of data, including time series data. We find that the computation of Shapley values has striking similarities to …

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

  5. Towards Effective Measurement of Membership Privacy Risk for Machine Learning Models

    … this memorization but at high computation cost. Shapley values is an alternative LOO approach with efficient algorithms in the literature. It measures the influence of a training data record on a model's utility and thereby the extent of it being memorized by that model. Hence, we conjecture that …

    waterloo Repository record for Towards Effective Measurement of Membership Privacy Risk for Machine Learning Models (opens in a new tab)

  6. Airbnb Valuation: A Machine Learning Approach

    … importance of these variables investigated using Shapley values.

    arkansas Repository record for Airbnb Valuation: A Machine Learning Approach (opens in a new tab)

  7. Ownership structure and corporate dividend policy

    … the outcome of the voting game. Using Shapley values as instruments for shareholder groups' voting powers, data on firms which traded on the Toronto Stock Exchange during the 1976-88 period are employed to test the model's predictions.

    ubc Repository record for Ownership structure and corporate dividend policy (opens in a new tab) Download PDF for Ownership structure and corporate dividend policy (opens in a new tab)

  8. Algorithms to Estimate Shapley Value Feature Attributions

    … features. In this class of explanation methods, Shapley value feature attributions have recently caught on. Although the Shapley value is appealing for its nice properties, it is NP-hard to compute in general. Here, we describe several works centered around tractably estimating the two most …

    washington Repository record for Algorithms to Estimate Shapley Value Feature Attributions (opens in a new tab)

  9. k-Label Dependent Evolutionary Distance Weighting for Software Defect Prediction

    … (MCC) as the fitness function. In addition, Shapley values are used to explain the importance of software features in defect predictions to provide insights into the interpretability of the model. The $k$-LDEDW model is then compared with graph neural networks (GNN), clustering techniques, …

    oxford-brookes Repository record for k-Label Dependent Evolutionary Distance Weighting for Software Defect Prediction (opens in a new tab) Download PDF for k-Label Dependent Evolutionary Distance Weighting for Software Defect Prediction (opens in a new tab)

  10. Data-Centric Machine Learning for Speech and Audio

    … recognition, we develop a method for estimating Shapley values of speech data for training an end-to-end neural ASR model, which performs a structured prediction task. We also demonstrate how data valuation can be used for environmental sound classification. In the context of ecoacoustic …

    cuny-grad Repository record for Data-Centric Machine Learning for Speech and Audio (opens in a new tab)

  11. A PREDICTIVE CARE FRAMEWORK FOR DIABETES & MATERNAL HEALTH: A MACHINE LEARNING APPROACH FROM PRECONCEPTION THROUGH POSTPARTUM PERIOD

    … a similar methodological approach by combining Shapley values with CatBoost tree ensembles. The novelty in explaining machine learning model decisions with metabolism domain knowledge is a paradigm shift as it allows us to understand the risk attributes, improving health literacy in public …

    nus Repository record for A PREDICTIVE CARE FRAMEWORK FOR DIABETES & MATERNAL HEALTH: A MACHINE LEARNING APPROACH FROM PRECONCEPTION THROUGH POSTPARTUM PERIOD (opens in a new tab) Download file for A PREDICTIVE CARE FRAMEWORK FOR DIABETES & MATERNAL HEALTH: A MACHINE LEARNING APPROACH FROM PRECONCEPTION THROUGH POSTPARTUM PERIOD (opens in a new tab)

  12. Machine Learning for Financial Crisis Prediction

    … in financial crisis prediction. We employ a Shapley value framework in an attempt to mitigate the black box nature of the machine-learning models. We show that the global economic climate is of vital importance in identifying banking and currency crises. Wages are shown to be the most …

    mcmaster Repository record for Machine Learning for Financial Crisis Prediction (opens in a new tab)

  13. Interpretability of Deep Learning Models for Time-Series Clinical Data

    … to explain time-series classifiers using Shapley values, which are a well-known method for determining the significance of features. The framework's objective is to improve the overall quality of explanations while reducing the computational complexity of generating Shapley values for …

    arizona-thes Repository record for Interpretability of Deep Learning Models for Time-Series Clinical Data (opens in a new tab)

  14. Self reported incompetence

    … confusion matrices, and the comparison of Shapley values for specific attribute values. Finally, my results indicate that detecting potentially impactful or interesting data records can be straightforward by calculating surprise scores, a novel method I propose.

    queens Repository record for Self reported incompetence (opens in a new tab)

  15. Unsupervised anomaly detection in financial transactions

    … Additionally, the models are explained using Shapley values in order to gather insights into which features contribute the most to classifying ledger entries as anomalous or regular. Lastly, the models are set up to run on Össur's Azure Machine Learning environment in order to facilitate …

    reykjavik Repository record for Unsupervised anomaly detection in financial transactions (opens in a new tab)

  16. Behavioral Modelling from Encrypted Remote Desktop Protocol Network Traffic

    … to one or more classes at the same time. I use Shapley Values to determine significant features and perform classification using the following techniques: SVM, KNN, Neural Network, Decision Tree, AdaBoost, Random Forest and XGBoost. The final model achieves a cross-validated minimum Precision of …

    queens Repository record for Behavioral Modelling from Encrypted Remote Desktop Protocol Network Traffic (opens in a new tab)

  17. Low-Resource Ecoacoustic Audio Classification

    … and introduce novel audio data valuation via Shapley values, revealing strategies to maximize performance and identify annotation inconsistencies, while finding self-supervised pre-training less impactful without extensive adaptation. Broadening the data sources, we develop a cross-modal …

    cuny-grad Repository record for Low-Resource Ecoacoustic Audio Classification (opens in a new tab)

  18. Transparent Machine Learning: Theory and Computation

    … of techniques to accelerate the computation of Shapley values, which are the basis of several popular algorithms; and (iii) a range of methods for performing feature selection with deep learning models, e.g., in unsupervised and adaptive settings. Many of these ideas are motivated by …

    washington Repository record for Transparent Machine Learning: Theory and Computation (opens in a new tab)

Page 1 of 4