책 이미지
책 정보
· 분류 : 외국도서 > 기술공학 > 기술공학 > 공학일반
· ISBN : 9789819963522
· 쪽수 : 127쪽
목차
1. Introduction
1.1 Building Blocks of AI
1.2 AI- Current State
1.3 Motivation
1.4 Need for Paradigm Shift
1.5 Summary
References
2. Model-Centric AI
2.1 Working Principle
2.2 Learning Methods
2.3 Model Building
2.4 Training
2.5 Testing
2.6 Model Tuning
2.7 Use Cases: Model-Centric AI
2.8 Summary
References
3. Data-Centric Principles for AI Engineering
3.1 Overview
3.2 AI Engineering
3.3 Challenges
3.4 Data-Centric Principles
3.5 Summary
References
4. Mathematical Foundation for Data Centric AI
4.1. Overview
4.2 Data tendency and distribution
4.3 Data models
4.4. Optimization techniques
4.5 Summary
References
5. Data-Centric AI
5.1 Data Acquisition
5.2 Data Labeling
5.3 Data Annotation
5.4 Data Augmentation
5.5 Data Deployment
5.6 Data-centric AI tools
5.7 Summary
References
6. Data-Centric AI in healthcare
6.1 Overview
6.2 Need and challenges of data centric approach
6.3 Application implementation in data-centric approach
6.4 Application implementation in model-centric approach
6.5 Comparison of Model Centric AI and Data Centric AI
6.6 Summary
References
7. Data-Centric AI in Mechanical Engineering
7.1 Overview
7.2 Need and challenges of data centric approach
7.3 Application implementation in data-centric approach
7.4 Application implementation in model-centric approach
7.5 Comparison of Model Centric AI and Data Centric AI
7.6 Summary
References
8. Data-Centric AI in Information Communication and Technology
8.1 Overview
8.2 Need and challenges of data centric approach
8.3 Application implementation in data-centric approach
8.4 Application implementation in model-centric approach
8.5 Comparison of Model Centric AI and Data Centric AI
8.6 Summary
References
9. Conclusion
9.1 Summary
9.2 Research Areas
References