Event Name: Faculty Development Programme (FDP) on “Unblocking AI Transparency: A Deep Dive into Explainable AI”
Date: 11th – 20th November 2024
Time: 3 PM to 7 PM
Mode: Online
Organizers: Electronics & ICT Academy, NIT Warangal
In Association With: Department of CSE (AI & ML), St. Peter’s Engineering College (Autonomous), Hyderabad
Sponsored by: Ministry of Electronics and Information Technology (MeitY), Government of India

Overview:

The Faculty Development Programme (FDP), titled “Unblocking AI Transparency: A Deep Dive into Explainable AI”, was organized to provide an in-depth understanding of Explainable Artificial Intelligence (XAI), an emerging field in AI that focuses on improving the transparency and interpretability of AI models. The event, conducted online, was held from 11th to 20th November 2024, from 3 PM to 7 PM daily. It aimed to empower faculty members, researchers, and industry professionals with the knowledge and tools necessary to make AI systems more understandable and trustworthy.

For Brochure please click here

Key Highlights:

• Resource Persons: The programme featured expert speakers and researchers from reputed institutions like NIT Warangal, industry professionals, and AI domain experts who provided deep insights into XAI concepts.
• Topics Covered:
  • Fundamentals of Explainable AI (XAI)
  • Current challenges in AI transparency
  • Techniques and tools to develop interpretable AI systems
  • Ethical considerations in AI decision-making
  • Hands-on sessions using real-world case studies and frameworks
  • Application of XAI in sectors like healthcare, finance, and autonomous systems.
• Target Audience: The programme was designed for faculty members, researchers, Ph.D. scholars, and professionals interested in AI and Machine Learning, providing them with advanced learning opportunities.

Interactive Sessions and Hands-On Learning:

The FDP included interactive sessions, where participants engaged in discussions with experts. The hands-on workshops enabled participants to apply the concepts learned during the theoretical sessions, using various XAI tools to solve real-world problems and evaluate AI systems for interpretability.

Outcomes:

• Participants gained a deep understanding of XAI techniques, enabling them to incorporate explainability in AI models.
• The programme enhanced participants’ ability to evaluate AI models critically and deploy AI systems that are both accurate and interpretable.
• Networking opportunities were provided for participants to collaborate on research and projects related to Explainable AI.