-
Notifications
You must be signed in to change notification settings - Fork 0
Explainability
Within Hoop we have a unique opportunity to add modules to a pipeline that can inspect and explain any problems or issues related to data interoperability. There are two types of explanation we are planning to add to the system:
-
Data clash explainability
-
Output format and interpretation explainability
Lane, H.C., Core, M.G., van Lent, M., Solomon, S., & Gomboc, D. (2005). Explainable artificial intelligence for training and tutoring. In Proceedings of the 12th International Conference on Artificial Intelligence (AIED 2005), Amsterdam, The Netherlands.
http://www.ict.usc.edu/~lane/papers/lane05-AIED.pdf
Core, M.G., Lane, H.C., van Lent, M., Gomboc, D., Solomon, S., & Rosenberg, M. (2006). Building Explainable Artificial Intelligence Systems, in Proceedings of the 18th Conference on Innovative Applications of Artificial Intelligence (IAAI-06), AAAI Press, Boston, MA.
http://www.aaai.org/Papers/IAAI/2006/IAAI06-010.pdf
An Explainable Artificial Intelligence System for Small-unit Tactical Behavior.
Michael van Lent, William Fisher, and Michael Mancuso. AAAI, page 900-907. AAAI Press / The MIT Press, (2004)
http://aaaipress.org/Papers/IAAI/2004/IAAI04-019.pdf