Keywords:
Artificial intelligence.
;
Electronic books.
Type of Medium:
Online Resource
Pages:
1 online resource (430 pages)
Edition:
1st ed.
ISBN:
9783030649494
Series Statement:
Studies in Computational Intelligence Series ; v.937
URL:
https://ebookcentral.proquest.com/lib/geomar/detail.action?docID=6531754
DDC:
006.3
Language:
English
Note:
Intro -- Preface -- Contents -- Explainable Artificial Intelligence for Process Mining: A General Overview and Application of a Novel Local Explanation Approach for Predictive Process Monitoring -- 1 Introduction -- 2 Background and Related Work -- 2.1 Process Mining -- 2.2 Predictive Business Process Management -- 2.3 Deep Learning for Predictive BPM and XAI -- 3 A Framework for Explainable Process Predictions -- 4 A Novel Local Post-Hoc Explanation Method -- 4.1 Binary Classification with Deep Learning -- 4.2 Local Region Identification by Using Neural Codes -- 4.3 Local Surrogate Model -- 5 Experiment Setting -- 5.1 Use Case: Incident Management -- 5.2 Evaluation Measures -- 5.3 Results -- 6 Discussion -- 7 Conclusion -- References -- Use of Visual Analytics (VA) in Explainable Artificial Intelligence (XAI): A Framework of Information Granules -- 1 Introduction -- 2 Explainability Strategies -- 2.1 Feature Selection -- 2.2 Performance Analysis -- 2.3 Model Explanations -- 3 Global and Local Interpretability -- 3.1 Information Scalability -- 3.2 Visual Scalability -- 4 Stability of Explanation -- 5 Visual Analytics for Granular Computing -- 6 Summary -- References -- Visualizing the Behavior of Convolutional Neural Networks for Time Series Forecasting -- 1 Introduction -- 2 Introduction to Neural Networks and Forecasting -- 2.1 Power Time Series Forecasting -- 2.2 Neural Networks -- 3 Relevant Literature -- 4 Training the cnn ae -- 4.1 Experiment -- 4.2 Data and Code -- 4.3 Setup -- 5 Visualization and Patterns -- 5.1 How to Interpret the Visualizations -- 5.2 Input Visualization -- 5.3 Kernel Visualization -- 5.4 Forecast Visualization -- 5.5 Activation Maps -- 5.6 How to Use the Individual Visualizations -- 6 Conclusion -- References -- Beyond Deep Event Prediction: Deep Event Understanding Based on Explainable Artificial Intelligence.
,
1 Introduction -- 2 Why Current Machine Learning is Differentiated from Human Learning -- 3 Beyond Deep Event Prediction -- 4 Big Data, AI, and Critical Condition -- 5 DUE Architecture -- 6 Properties of DUE -- 7 The Concept of DUE -- 7.1 Human Critical Thinking -- 7.2 Contextual Understanding -- 8 Learning Model for DUE -- 8.1 Fundamental Computing for DUE -- 8.2 Computing Using CBNs-Based XAI -- 9 DUE Trends and Future Outlooks -- 9.1 Disasters -- 9.2 Economic Consequences -- 9.3 Safety and Security -- 10 Conclusions -- References -- Interpretation of SVM to Build an Explainable AI via Granular Computing -- 1 Introduction -- 1.1 The Era of Explainable AI with Granular Computing -- 2 The Problem with a Gap in Explainability -- 3 Related Work -- 4 Background -- 4.1 SVM Algorithm -- 4.2 Granular Computing -- 4.3 Syllogisms -- 4.4 Explainable Artificial Intelligence -- 5 Research Methodologies -- 5.1 A Constructive Approach in Developing XAI -- 5.2 A Human-Centric Approach at Early Development Stage -- 6 Implementation: A Syllogistic Approach to Interpret SVM's Classification from Information Granules -- 6.1 Data Selection -- 6.2 Identifying the Information Granules from These Data Sets -- 6.3 Analyzing and Interpretation of Syllogisms from SVM -- 6.4 The General Framework for Modelling Syllogistic Rules -- 6.5 Validating the Interpreted Syllogistic Rules with Physicians and CPGs -- 6.6 XAI Knowledge Base for CAD -- 6.7 XAI with Inference Engine -- 6.8 User Interface in Mobile Application -- 6.9 Preliminary Results -- 6.10 Iterative Retuning and Validation of XAI Mobile App with Physicians in the Loop -- 7 Final XAI Mobile App -- 7.1 XAI Mobile App -- 8 Testing Results from XAI Mobile App -- 8.1 Testing Phase I -- 8.2 Testing Phase II -- 8.3 Testing Phase III -- 8.4 Results from Testing -- 9 Conclusion and Discussion -- 10 Future Work -- References.
,
Factual and Counterfactual Explanation of Fuzzy Information Granules -- 1 Introduction -- 2 Background -- 3 Proposal -- 4 Illustrative Use Case -- 5 Experiments -- 5.1 Experimental Settings -- 5.2 Experiment 1: Relevance of Expert Knowledge-Based Counterfactual Explanations -- 5.3 Experiment 2: An Impact of Posterior Linguistic Approximation -- 6 Discussion -- 7 Conclusion and Future Work -- References -- Transparency and Granularity in the SP Theory of Intelligence and Its Realisation in the SP Computer Model -- 1 Introduction -- 2 Introduction to Transparency -- 3 Introduction to Granularity -- 4 The SP System in Brief -- 4.1 Information Compression -- 4.2 Abstract View of the SP System -- 4.3 Basic Structures in the SP System for Representing Knowledge -- 4.4 The Concept of SP-Multiple-Alignment -- 4.5 Unsupervised Learning -- 4.6 Existing and Potential Strengths of the SP System -- 4.7 SP-Neural -- 4.8 Future Developments -- 5 Information Compression and the Representation and Processing of Knowledge in the SP System -- 5.1 Information Compression via the Matching and Unification of Patterns -- 5.2 Discontinuous Patterns -- 5.3 Seven Variants of ICMUP -- 5.4 The DONSVIC Principle -- 5.5 Ideas Related to the Concept of a Granule -- 5.6 Tying Things Together? -- 6 Transparency via Audit Trails -- 7 Transparency via Granularity and Familiarity -- 7.1 Granularity, Familiarity, and Basic ICMUP -- 7.2 Granularity, Familiarity, and Chunking-With-Codes -- 7.3 Granularity, Familiarity, and Schema-Plus-Correction -- 7.4 Granularity, Familiarity, and Run-Length Encoding -- 7.5 Granularity, Familiarity, and Part-Whole Hierarchies -- 7.6 Granularity, Familiarity, and Class-Inclusion Hierarchies -- 7.7 Granularity, Familiarity, and SP-multiple-alignments -- 8 Interpretability and Explainability -- 9 Conclusion -- References.
,
Survey of Explainable Machine Learning with Visual and Granular Methods Beyond Quasi-Explanations -- 1 Introduction -- 1.1 What Are Explainable and Explained? -- 1.2 Types of Machine Learning Models -- 1.3 Informal Definitions -- 1.4 Formal Operational Definitions -- 1.5 Interpretability and Granularity -- 2 Foundations of Interpretability -- 2.1 How Interpretable Are the Current Interpretable Models? -- 2.2 Domain Specificity of Interpretations -- 2.3 User Centricity of Interpretations -- 2.4 Types of Interpretable Models -- 2.5 Using Black-Box Models to Explain Black Box Models -- 3 Overview of Visual Interpretability -- 3.1 What is Visual Interpretability? -- 3.2 Visual Versus Non-Visual Methods for Interpretability and Why Visual Thinking -- 3.3 Visual Interpretation Pre-Dates Formal Interpretation -- 4 Visual Discovery of ML Models -- 4.1 Lossy and Lossless Approaches to Visual Discovery in n-D Data -- 4.2 Theoretical Limitations -- 4.3 Examples of Lossy Versus Lossless Approaches for Visual Model Discovery -- 5 General Line Coordinates (GLC) -- 5.1 General Line Coordinates to Convert n-D Points to Graphs -- 5.2 Case Studies -- 6 Visual Methods for Traditional Machine Learning -- 6.1 Visualizing Association Rules: Matrix and Parallel Sets Visualization for Association Rules -- 6.2 Dataflow Tracing in ML Models: Decision Trees -- 6.3 IForest: Interpreting Random Forests via Visual Analytics -- 6.4 TreeExplainer for Tree Based Models -- 7 Traditional Visual Methods for Model Understanding: PCA, t-SNE and Related Point-to-Point Methods -- 8 Interpreting Deep Learning -- 8.1 Understanding Deep Learning via Generalization Analysis -- 8.2 Visual Explanations for DNN -- 8.3 Rule-Based Methods for Deep Learning -- 8.4 Human in the Loop Explanations -- 8.5 Understanding Generative Adversarial Networks (GANs) via Explanations.
,
9 Open Problems and Current Research Frontiers -- 9.1 Evaluation and Development of New Visual Methods -- 9.2 Cross Domain Pollination: Physics & -- Domain Based Methods -- 9.3 Cross-Domain Pollination: Heatmap for Non-Image Data -- 9.4 Future Directions -- 10 Conclusion -- References -- MiBeX: Malware-Inserted Benign Datasets for Explainable Machine Learning -- 1 Introduction -- 2 Background and Related Works -- 2.1 Malware Analysis Overview -- 2.2 Granularity in Malware Analysis -- 2.3 Feature Visualization -- 2.4 Malware as Video -- 2.5 MetaSploit -- 2.6 Bash Commands -- 3 Dataset Generation -- 3.1 Gathering Benign Files -- 3.2 Trojan Insertion -- 3.3 Malware Verification -- 3.4 Dataset Generation Results -- 4 Malware Classification -- 4.1 Pre-processing -- 4.2 Network Specifications -- 4.3 Classification Results -- 5 Saliency Mapping -- 6 Conclusion and Future Work -- References -- Designing Explainable Text Classification Pipelines: Insights from IT Ticket Complexity Prediction Case Study -- 1 Introduction -- 2 Related Work -- 2.1 Explainability and Granularity -- 2.2 Text Representation -- 2.3 Text Classification -- 2.4 Ticket Classification Research -- 2.5 Summary -- 3 Methods -- 3.1 Feature Extraction -- 3.2 Machine Learning Classifiers -- 4 Experimental Evaluation -- 4.1 Case Study and Datasets -- 4.2 Experimental Settings -- 4.3 Comparison of SUCCESS and QuickSUCCESS -- 4.4 Results -- 5 Discussion -- 5.1 Explainability and Granularity Implications -- 5.2 Methodological Contributions -- 5.3 Managerial and Practical Contributions -- 6 Conclusion and Future Works -- Appendix I: Taxonomy of Decision-Making Logic Levels -- Appendix II: Business Sentiment Lexicon with Assigned Valences -- References -- A Granular Computing Approach to Provide Transparency of Intelligent Systems for Criminal Investigations -- 1 Introduction.
,
2 Supporting Intelligence Analysts with Intelligent Systems.
Permalink