What You Need to Know Before
You Start
Starts 6 June 2025 12:12
Ends 6 June 2025
00
days
00
hours
00
minutes
00
seconds
55 minutes
Optional upgrade avallable
Not Specified
Progress at your own speed
Free Video
Optional upgrade avallable
Overview
Explore formal models of machine teaching without collusion in this theoretical talk on trustworthy AI by Sandra Zilles from the University of Regina.
Syllabus
- Introduction to Machine Teaching
- Formal Models of Machine Teaching
- Trust and Collusion in Machine Teaching
- Non-Collusive Teaching Strategies
- Mathematical Foundations
- Practical Applications
- Future Directions in Machine Teaching
- Conclusion and Discussion
Definitions and fundamental concepts
Historical context and evolution
Key frameworks and methodologies
Comparison with traditional machine learning models
Defining trust in AI systems
Identifying collusion risks and mitigation strategies
Designing trustworthy teaching models
Case studies of successful non-collusive implementations
Algorithmic approaches to teaching without collusion
Theoretical limits and capabilities
Real-world examples of machine teaching
Industry scenarios and potential impact
Emerging trends and research areas
Ethical considerations and policy implications
Review of key concepts
Open forum for questions and future inquiry proposals
Subjects
Computer Science