This book presents a semantic-based explainable framework based on knowledge graph and semantic web technology. It focuses on designing XAI system that transforms black-box AI model into a comprehensive and meaningful AI model that users can leverage. Stack of technologies categorized under semantic web technologies is covered for the semantic explanation framework. It discussed ontology using OWL for capturing concepts and the relationship amongst concepts in the domain of discourse. Knowledge graph using Linked Open data (LOD) technology is covered for integrating formalized knowledge. The book also includes First Order Logic (FOL)-mathematical tool, as the foundation of knowledge representation and reasoning.
• Explain ability challenges of the existing deep learning-based AI model also termed as black box model, will be possible to be addressed by the implementation of the innovative technology.
• Enables to design of higher-level intelligence compared to the current AI system supports and thus revolutionises the entire automation domain.
• Assists AI professionals to get an insight into mathematical tools such as First Order Logic (FOL) and Description Logic(DL) for explicit knowledge representation.
• Helps to formalise knowledge required for machine intelligence using semantic web technologies
• Studies implications of XAI intelligent system developed for medical diagnosis, Fraud detection, Autonomous vehicles, hiring decisions, Legal decisions etc. for making decisions.
Researchers, students and professionals working on Computational Intelligence, Machine Learning, and Artificial Intelligence in the fields of computer science, computer engineering and information technology will find this book useful.
Table of Contents:
1. Integration of Deep Learning – based AI Model with Explainable AI (XAI) 2. Unlocking the Potential of Knowledge Graphs through Completion Techniques 3. Symbolic System, Neural Network and Semantic Web Technology Integration for Deep Learning 4. Mathematical Tools for Knowledge Representation 5. Cognitive Computational Systems Integrating Machine Learning and Automated Reasoning 6. Symbolic Knowledge Representation by ANN 7. Knowledge Representation for Human and Machine-Centric Explanations 8. Explainable AI: Bridging the Gap between Complexity and Interpretability 9. Interpretability, Transparency Assessment of AI Systems 10. Addressing Trustworthiness and Explainability Using Knowledge Graph 11. The Power of Automation: Exploring Robotic Process the Journey from Automation Theory to Implementation 12. Explainable Artificial Intelligence with Open Source Software 13. Knowledge Graph and Semantic Web Technology-based XAI Application of XAI in Different Domains 14. Developing Brain-Driven Systems Using Medical Image-Based Cognitive Intelligence and Machine Learning-Reasoning
