AI Assurance: Towards Trustworthy, Explainable, Safe, and Ethical AI provides readers with solutions and a foundational understanding of the methods that can be applied to test AI systems and provide assurance. Anyone developing software systems with intelligence, building learning algorithms, or deploying AI to a domain-specific problem (such as allocating cyber breaches, analyzing causation at a smart farm, reducing readmissions at a hospital, ensuring soldiers’ safety in the battlefield, or predicting exports of one country to another) will benefit from the methods presented in this book.
As AI assurance is now a major piece in AI and engineering research, this book will serve as a guide for researchers, scientists and students in their studies and experimentation. Moreover, as AI is being increasingly discussed and utilized at government and policymaking venues, the assurance of AI systems—as presented in this book—is at the nexus of such debates.
1. 1 An introduction to AI assurance - p. 1 2. 2 Setting the goals for ethical, unbiased, and fair AI - p. 13 3. 3 An overview of explainable and interpretable AI☆☆ George Mason University's Office of the Provost funded some of this research. - p. 55 4. 3.1: Introduction - p. 56 5. 3.2: Methods and materials - p. 59 6. 3.3: Experiments using XAI models - p. 104 7. 3.4: Discussion - p. 112 8. 3.5: Future work - p. 115 9. 3.6: Conclusion - p. 116 10. References - p. 116 11. 4 Bias, fairness, and assurance in AI: overview and synthesis - p. 125 12. 5 An evaluation of the potential global impacts of AI assurance - p. 153 13. 6 The role of inference in AI: Start S.M.A.L.L. with mindful modeling☆☆ S.M.A.L.L. is an acronym for Specific-Mindful-Attainable-Limited-Lucid. - p. 183 14. 7 Outlier detection using AI: a survey - p. 231 15. 8 AI assurance using causal inference: application to public policy - p. 293 16. 9 Data collection, wrangling, and pre-processing for AI assurance - p. 321 17. 10 Coordination-aware assurance for end-to-end machine learning systems: the R3E approach - p. 339 18. 11 Assuring AI methods for economic policymaking - p. 369 19. 12 Panopticon implications of ethical AI: equity, disparity, and inequality in healthcare - p. 429 20. 13 Recent advances in uncertainty quantification methods for engineering problems - p. 453 21. 14 Socially responsible AI assurance in precision agriculture for farmers and policymakers - p. 473 22. 15 The application of artificial intelligence assurance in precision farming and agricultural economics - p. 501 23. 16 Bringing dark data to light with AI for evidence-based policymaking - p. 531 24. Index - p. 559
AI Assurance: Towards Trustworthy, Explainable, Safe, and Ethical AI provides readers with solutions and a foundational understanding of the methods that can be applied to test AI systems and provide assurance. Anyone developing software systems with intelligence, building learning algorithms, or deploying AI to a domain-specific problem (such as allocating cyber breaches, analyzing causation at a smart farm, reducing readmissions at a hospital, ensuring soldiers’ safety in the battlefield, or predicting exports of one country to another) will benefit from the methods presented in this book.
As AI assurance is now a major piece in AI and engineering research, this book will serve as a guide for researchers, scientists and students in their studies and experimentation. Moreover, as AI is being increasingly discussed and utilized at government and policymaking venues, the assurance of AI systems—as presented in this book—is at the nexus of such debates.
1. 1 An introduction to AI assurance - p. 1 2. 2 Setting the goals for ethical, unbiased, and fair AI - p. 13 3. 3 An overview of explainable and interpretable AI☆☆ George Mason University's Office of the Provost funded some of this research. - p. 55 4. 3.1: Introduction - p. 56 5. 3.2: Methods and materials - p. 59 6. 3.3: Experiments using XAI models - p. 104 7. 3.4: Discussion - p. 112 8. 3.5: Future work - p. 115 9. 3.6: Conclusion - p. 116 10. References - p. 116 11. 4 Bias, fairness, and assurance in AI: overview and synthesis - p. 125 12. 5 An evaluation of the potential global impacts of AI assurance - p. 153 13. 6 The role of inference in AI: Start S.M.A.L.L. with mindful modeling☆☆ S.M.A.L.L. is an acronym for Specific-Mindful-Attainable-Limited-Lucid. - p. 183 14. 7 Outlier detection using AI: a survey - p. 231 15. 8 AI assurance using causal inference: application to public policy - p. 293 16. 9 Data collection, wrangling, and pre-processing for AI assurance - p. 321 17. 10 Coordination-aware assurance for end-to-end machine learning systems: the R3E approach - p. 339 18. 11 Assuring AI methods for economic policymaking - p. 369 19. 12 Panopticon implications of ethical AI: equity, disparity, and inequality in healthcare - p. 429 20. 13 Recent advances in uncertainty quantification methods for engineering problems - p. 453 21. 14 Socially responsible AI assurance in precision agriculture for farmers and policymakers - p. 473 22. 15 The application of artificial intelligence assurance in precision farming and agricultural economics - p. 501 23. 16 Bringing dark data to light with AI for evidence-based policymaking - p. 531 24. Index - p. 559
