What You Need to Know Before
You Start

Starts 6 June 2025 12:46

Ends 6 June 2025

00 days
00 hours
00 minutes
00 seconds
course image

Theoretical Aspects of Trustworthy AI

Discover theoretical aspects of trustworthy AI in this insightful talk by Susmit Jha from SRI International, exploring key concepts and challenges in the field.
Simons Institute via YouTube

Simons Institute

2484 Courses


50 minutes

Optional upgrade avallable

Not Specified

Progress at your own speed

Free Video

Optional upgrade avallable

Overview

Discover theoretical aspects of trustworthy AI in this insightful talk by Susmit Jha from SRI International, exploring key concepts and challenges in the field.

Syllabus

  • Introduction to Trustworthy AI
  • Definition and importance of trustworthy AI
    Overview of trust in AI systems
  • Key Concepts in Trustworthy AI
  • Fairness and bias mitigation in AI
    Explainability and interpretability
    Robustness and reliability in AI models
  • Theoretical Foundations
  • Formal methods in AI
    Verification and validation techniques
    The role of logic and reasoning in trustworthy AI
  • Challenges in Trustworthy AI
  • Scalability of trustworthy systems
    Handling uncertainty and probabilistic reasoning
    Addressing ethical and societal implications
  • Case Studies and Applications
  • Real-world examples of trustworthy AI systems
    Analysis of failures and trust breaches in AI
  • Future Directions in Trustworthy AI
  • Emerging technologies and their impact on trust
    Advancements in AI safety and governance
  • Conclusion
  • Recap of key concepts
    Open questions and areas for further research

Subjects

Computer Science