Explainable AI (XAI) Section
Chair: Asim Roy
Email: [email protected]


WCCI 2024: AI & Regulations Section Meeting

You are invited to view the presentation slides from the AI & Regulations Section Meeting, held on 2 July at WCCI 2024 in Yokohama, Japan.

View the Presentation Slides

Motivation

The black-box nature of deep learning models is preventing deployment of critical AI applications in defense, medicine, and other areas because of the potential risk of wrong decisions from such models and not understanding why it took such a decision. If the models were transparent in some form and we understood how they worked and made decisions, then such risks would disappear. Thus, creating some form of explainable and interpretable models out of deep learning models has become a critical research area for the machine learning community. It is also a high-priority research area at most national funding agencies such as the NSF (National Science Foundation) and DARPA (Defense Advanced Research Projects Agency) in the US. Once we have acceptable forms of explainability or interpretability of these models, it would lead to the deployment and use of AI on a scale that we have yet to see. And the economic impact of an extensive deployment of AI worldwide would be in the trillions of dollars in the years to come and produce unprecedented changes to our society. Such is the potential of Explainable AI.

This section is all about getting involved and jointly creating this new technology of Explainable AI that the world is waiting for.


Objectives

The main objective of the Section on XAI is to be the focal point of scientific exchange in this emerging area. More specifically, the Section and its members will:

  • Organize workshops, special sessions, panels, tutorials at high profile conferences
  • Engage the industry through plenary talks, sponsorship, etc.
  • Organize special issues in leading journals
  • Initiate and maintain an e-Newsletter on XAI involving the leading industry representatives

Structure of the Explainable AI (XAI) Section

The XAI Section is currently chaired by Prof. Asim Roy of Arizona State University, who proposed this Section to INNS.


Membership

Membership will be open to all INNS members interested in Explainable AI.


 

How to join?

Here’s the link to the membership application form:

Section Membership Application