Explaining data patterns using knowledge from the web of data [electronic resource]

• 作者： Tiddi, Ilaria, author.
• 其他作者：
  • IOS Press.
• 其他題名：
  • Studies on the Semantic Web ;
• 出版： Amsterdam, Netherlands : IOS Press
• 叢書名： Studies on the semantic web ;vol. 034
• 主題： Data mining. , Electronic books.
• ISBN： 9781614998600 (electronic bk.) 、 1614998604 (electronic bk.)
• FIND@SFXID: CGU
• 資料類型: 電子書
• 內容註: Includes bibliographical references. Intro; Title Page; Contents; Introduction and State of the Art; Introduction; Problem Statement; Research Hypothesis; Research Questions; RQ1: Definition of an Explanation; RQ2: Detection of the Background Knowledge; RQ3: Generation of the Explanations; RQ4: Evaluation of the Explanations; Research Methodology; Approach and Contributions; Applicability; Dedalo at a Glance; Contributions of the Thesis; Structure of the Thesis; Structure; Publications; Datasets and Use-cases; State of the Art; A Cognitive Science Perspective on Explanations; Characterisations of Explanations. The Explanation OntologyResearch Context; The Knowledge Discovery Process; Graph Terminology and Fundamentals; Historical Overview of the Web of Data; Consuming Knowledge from the Web of Data; Resources; Methods; Towards Knowledge Discovery from the Web of Data; Managing Graphs; Mining Graphs; Mining the Web of Data; Summary and Discussion; Looking for Pattern Explanations in the Web of Data; Manually generating Explanations; Introduction; The Inductive Logic Programming Framework; General Setting; Generic Technique; A Practical Example; The ILP Approach to Generate Explanations; Experiments. Building the Training ExamplesBuilding the Background Knowledge; Inducing Hypotheses; Discussion; Conclusions and Limitations; Automatically generating Explanations; Introduction; Problem Formalisation; Assumptions; Formal Definitions; An Example; Automatic Discovery of Explanations; Challenges and Proposed Solutions; Description of the Process; Evaluation Measures; Final Algorithm; Experiments; Use-cases; Heuristics Comparison; Best Explanations; Time Evaluation; Conclusions and Limitations; Aggregating Explanations using Neural Networks; Introduction; Motivation and Challenges. Improving Atomic RulesRule Interestingness Measures; Neural Networks to Predict Combinations; Proposed Approach; A Neural Network Model to Predict Aggregations; Integrating the Model in Dedalo; Experiments; Comparing Strategies for Rule Aggregation; Results and Discussion; Conclusions and Limitations; Contextualising Explanations with the Web of Data; Introduction; Problem Statement; Learning Path Evaluation Functions through Genetic Programming; Genetic Programming Foundations; Preparatory Steps; Step-by-Step Run; Experiments; Experimental Setting; Results; Conclusion and Limitations. Evaluation and ConclusionEvaluating Dedalo with Google Trends; Introduction; First Empirical Study; Data Preparation; Evaluation Interface; Evaluation Measurements; Participant Details; User Agreement; Results, Discussion and Error Analysis; Second Empirical Study; Data Preparation; Evaluation Interface; Evaluation Measurements; User Agreement; Results, Discussion and Error Analysis; Final Discussion and Conclusions; Discussion and Conclusions; Introduction; Summary, Answers and Contributions; Definition of an Explanation; Detection of the Background Knowledge; Generation of the Explanations.
• More
• 讀者標籤：

  需登入
• 引用連結：

  Copy Link
• 目前引用數
• Share: