Engineering AI Systems

by Len Bass; Qinghua Lu; Ingo Weber; Liming Zhu

Artificial Intelligence

Book Details

Book Title

Engineering AI Systems

Author

Len Bass; Qinghua Lu; Ingo Weber; Liming Zhu

Publisher

Addison-Wesley

Publication Date

2025

ISBN

9780138261450

Number of Pages

613

Language

English

Format

PDF

File Size

7.1MB

Subject

Artificial Intelligence

Table of Contents

  • Cover Page
  • About This eBook
  • Title Page
  • Copyright Page
  • Contents
  • Preface
  • Acknowledgments
  • About the Authors
  • 1. Introduction
  • 1.1 What We Talk about When We Talk about Things: Terminology
  • 1.2 Achieving System Qualities
  • 1.3 Life-Cycle Processes
  • 1.4 Software Architecture
  • 1.5 AI Model Quality
  • 1.6 Dealing with Uncertainty
  • 1.7 Summary
  • 1.8 Discussion Questions
  • 1.9 For Further Reading
  • 2. Software Engineering Background
  • 2.1 Distributed Computing
  • 2.2 DevOps Background
  • 2.3 MLOps Background
  • 2.4 Summary
  • 2.5 Discussion Questions
  • 2.6 For Further Reading
  • 3. AI Background
  • 3.1 Terminology
  • 3.2 Selecting a Model
  • 3.3 Preparing the Model for Training
  • 3.4 Summary
  • 3.5 Discussion Questions
  • 3.6 For Further Reading
  • 4. Foundation Models
  • 4.1 Foundation Models
  • 4.2 Transformer Architecture
  • 4.3 Alternatives in FM Architectures
  • 4.4 Customizing FMs
  • 4.5 Designing a System Using FMs
  • 4.6 Maturity of FMs and Organizations
  • 4.7 Challenges of FMs
  • 4.8 Summary
  • 4.9 Discussion Questions
  • 4.10 For Further Reading
  • 5. AI Model Life Cycle
  • 5.1 Developing the Model
  • 5.2 Building the Model
  • 5.3 Testing the Model
  • 5.4 Release
  • 5.5 Summary
  • 5.6 Discussion Questions
  • 5.7 For Further Reading
  • 6. System Life Cycle
  • 6.1 Design
  • 6.2 Developing Non-AI Modules
  • 6.3 Build
  • 6.4 Test
  • 6.5 Release and Deploy
  • 6.6 Operate, Monitor, and Analyze
  • 6.7 Summary
  • 6.8 Discussion Questions
  • 6.9 For Further Reading
  • 7. Reliability
  • 7.1 Fundamental Concepts
  • 7.2 Preventing Faults
  • 7.3 Detecting Faults
  • 7.4 Recovering from Faults
  • 7.5 Summary
  • 7.6 Discussion Questions
  • 7.7 For Further Reading
  • 8. Performance
  • 8.1 Efficiency
  • 8.2 Accuracy
  • 8.3 Summary
  • 8.4 Discussion Questions
  • 8.5 For Further Reading
  • 9. Security
  • 9.1 Fundamental Concepts
  • 9.2 Approaches to Mitigating Security Concerns
  • 9.3 Summary
  • 9.4 Discussion Questions
  • 9.5 For Further Reading
  • 10. Privacy and Fairness
  • 10.1 Privacy in AI Systems
  • 10.2 Fairness in AI Systems
  • 10.3 Achieving Privacy
  • 10.4 Achieving Fairness
  • 10.5 Summary
  • 10.6 Discussion Questions
  • 10.7 For Further Reading
  • 11. Observability
  • 11.1 Fundamental Concepts
  • 11.2 Evolving from Monitorability to Observability
  • 11.3 Approaches for Enhancing Observability
  • 11.4 Summary
  • 11.5 Discussion Questions
  • 11.6 For Further Reading
  • 12. The Fraunhofer Case Study
  • 12.1 The Problem Context
  • 12.2 Case Study Description and Setup
  • 12.3 Summary
  • 12.4 Takeaways
  • 12.5 Discussion Questions
  • 12.6 For Further Reading
  • 13. The ARM Hub Case Study
  • 13.1 Introduction
  • 13.2 Our Approach
  • 13.3 LLMs in SME Manufacturing
  • 13.4 A RAG-Based Chatbot for SME Manufacturing
  • 13.5 Architecture of the ARM Hub Chatbot
  • 13.6 MLOps in ARM Hub
  • 13.7 Ongoing Work
  • 13.8 Summary
  • 13.9 Takeaways
  • 13.10 Discussion Questions
  • 13.11 For Further Reading
  • 14. The Banking Case Study
  • 14.1 Customer Churn Prediction
  • 14.2 Key Challenges in the Banking Sector
  • 14.3 Summary
  • 14.4 Takeaways
  • 14.5 Discussion Questions
  • 14.6 For Further Reading
  • 15. The Future of AI Engineering
  • 15.1 The Shift to DevOps 2.0
  • 15.2 AI’s Implications for the Future
  • 15.3 AIWare or AI-as-Software
  • 15.4 Trust in AI and the Role of Human Engineers
  • 15.5 Summary
  • 15.6 Discussion Questions
  • 15.7 For Further Reading
  • References
  • Index