NIST has made a call for public thoughts and comments about the Four Principals of Explainable AI since “AI must be explainable to society to enable understanding, trust, and adoption of new AI technologies, the decisions produced, or guidance provided by AI systems.” The August 17, 2020 “Call for Comments on Four Principles of Explainable Artificial Intelligence” briefly describe these “…four principles of explainable AI”:
-
Explanation: Systems deliver
accompanying evidence or reason(s) for all outputs.
- Meaningful:
Systems provide explanations that are understandable to
individual users.
- Explanation
Accuracy: The explanation correctly
reflects the system's process for generating the
output.
- Knowledge Limits: The system only operates under conditions for which it was designed or when the system reaches a sufficient confidence in its output.
Please make comments which will be accepted until October 15, 2020 and there will no editing or redacting of comments.
Originally published 19 August, 2020
The content of this article is intended to provide a general guide to the subject matter. Specialist advice should be sought about your specific circumstances.