Knowledge-Infused Learning: Neurosymbolic AI for Explainability, Interpretability, and Safety

Knowledge-infused learning directly confronts the opacity of current 'black-box' AI models by combining data-driven machine learning techniques with the structured insights of symbolic AI. This guidebook introduces the pioneering techniques of neurosymbolic AI, which blends statistical models with symbolic knowledge to make AI safer and user-explainable. This is critical in high-stakes AI applications in healthcare, law, finance, and crisis management. The book brings readers up to speed on advancements in statistical AI, including transformer models such as BERT and GPT, and provides a comprehensive overview of weakly supervised, distantly supervised, and unsupervised learning methods alongside their knowledge-enhanced variants. Other topics include active learning, zero-shot learning, and model fusion. Beyond theory, the book presents practical considerations and applications of neurosymbolic AI in conversational systems, mental health, crisis management systems, and social and behavioral sciences, making it a pragmatic reference for AI system designers in academia and industry.

Table of Contents:
1. Introduction; 2. Knowledge graphs for explainability and interpretability; 3. Knowledge-infused learning: the subsumer to neurosymbolic AI; 4. Shallow infusion of knowledge; 5. Semi-deep infusion learning; 6. Deep knowledge-infused learning; 7. Process knowledge-infused learning; 8. Knowledge-infused conversational NLP; 9. Neurosymbolic large language models; References; Index.

Review :
'Professor Amit Sheth is a leading expert in knowledge-fused learning. The topics covered by this book are important to advance state-of-the-art AI. As our understanding of generative AI deepens, we ask what the next frontiers of AI are. This timely book offers a refreshing answer that explores AI research beyond large language models.' Huan Liu, Arizona State University 'This timely and insightful book by Manas Gaur and Amit Sheth combines data-driven AI with structured human knowledge, creating a practical pathway toward transparent and safe AI. Addressing critical gaps in AI's explainability and interpretability, especially in healthcare and crisis management, the authors introduce 'Knowledge-infused Learning'-an essential approach for human-centric AI. Their innovative frameworks, like CREST, are thoughtfully designed for real-world impact. For anyone deeply engaged in multimodal AI, digital health, or responsible technology use, this book is a must-read guide, offering robust technical foundations and thoughtful ethical considerations crucial for equitable AI solutions.' Ramesh Jain, University of California, Irvine 'Knowledge-Infused Learning is a timely and essential guide to building AI systems that are not only powerful, but also interpretable and trustworthy. Gaur and Sheth brilliantly show how integrating human knowledge with machine learning leads to more explainable, safer, and more responsible AI. A must-read for anyone shaping the future of intelligent systems.' Craig Knoblock, Information Sciences Institute, University of Southern California