Technical Workshop "Exploring Explainable AI: Methods, Challenges, and Practical Applications" By: Nasrin Tavakoli

Friday, February 2, 2024 - 12:00 to 13:00

Exploring Explainable AI: Methods, Challenges, and Practical Applications
Presenter: Nasrin Tavakoli


Date: Friday, February 2nd, 2024
Time:12:00 PM- 1:00 PM
Location: 4th Floor (Workshop space) at 300 Ouellette Avenue (School of Computer Science Advanced Computing Hub)

 

Abstract:
As AI systems become more prevalent in our daily lives, understanding their decision-making processes and ensuring transparency and accountability are crucial. This workshop aims to provide participants with a comprehensive overview of Explainable AI, its methods, challenges, and practical applications. Problem Statement: The lack of transparency in AI systems can lead to biased outcomes, ethical concerns, and limited user trust. Explainable AI offers a solution to these issues by providing insights into the decision-making processes of AI models.
The workshop will combine theoretical discussions and hands-on demonstrations to engage participants in understanding and applying Explainable AI methods. As a result, participants will gain a deeper understanding of the challenges and potential solutions in achieving explainability for AI systems. They will also learn how to evaluate and apply different Explainable AI methods based on their specific use cases.

Workshop Outline:
  • Introduction to Explainable AI
  • Why explainable AI matters
  • How explainable AI works
  • Benefits of explainable AI
  • Methods and Approaches
  • Challenges and Considerations
  • Conclusion
Prerequisites:

Basic Understanding of Machine Learning and AI

Understanding of Model Training and Evaluation
 
Biography:
Nasrin Tavakoli is a Ph.D. student of Computer Science at the University of Windsor. Her field of study has been Artificial Intelligence and Machine Learning. During her master's program, she worked on breast cancer diagnosis based on deep features. She is continuing her research in Artificial Intelligence, specifically on Explainable AI, in the Ph.D. program.