Overview

• Focus: The practical implementation of Safe & Trustworthy AI in real-world systems.
• Scope: Covers AI in high-stakes applications like robotics, self-driving cars, and autonomous aircraft.
• Key Themes:

• Ensuring AI is reliable, robust, and predictable.
• Solving challenges of real-time decision-making in unpredictable environments.
• How AI perceives, decides, and learns safely.

• Relevance: Essential for understanding the responsible deployment of next-generation autonomous technology.

Objectives of Event

To provide a comprehensive understanding of the practical implementation and critical challenges of Safe AI in real-world autonomous systems like robots, cars, and planes. Key Aims:

• Explain core "Safety by Design" principles for autonomous systems.
• Showcase real-world applications and technical challenges.
• Highlight the societal impact and need for trustworthy AI.
• Facilitate knowledge exchange with an international expert.

Convener Details

• Dr. Sudeep Varshney, sudeep.varshney@sharda.ac.in

Co-ordinators:

• Dr. Gaurav Raj, 8587010020, gaurav.raj@sharda.ac.in

Speaker Details:

• Dr. IAN GRAY, Senior Lecturer, Computer Science, University of York, UK