NIST News:
A multidisciplinary team of computer scientists, cognitive scientists, mathematicians, and specialists in AI and machine learning who all have diverse background and research specialties, explore and define the core tenets of explainable AI (XAI).
The team aims to develop measurement methods and best practices that support the implementation of those tenets.
Ultimately, the team plans to develop a metrologist’s guide to AI systems that address the complex entanglement of terminology and taxonomy as it relates to the myriad layers of the AI field.
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.
Call for comments on four principles of explainable artificial intelligence
Thank you for your interest in commenting on the first draft of Four Principles of Explainable Artificial Intelligence (NISTIR 8312). The paper presents four principles that capture the fundamental properties of explainable Artificial Intelligence (AI) systems.
These principles are heavily influenced by an AI system’s interaction with the human receiving the information. The requirements of the given application, the task, and the consumer of the explanation will influence the type of explanation deemed appropriate. Our four principles are intended to capture a broad set of motivations, applications, and perspectives.
To characterize the diverse methods, applications, and perspectives of explainable AI, we are seeking comments on our white paper. Please submit comments by email to explainable-AI@nist.gov. We encourage you to submit comments using the form provided on this page. Anonymous comments are accepted. However, including your name and contact information enables the authors to contact you for clarification if necessary.
All comments will be made public as-is, with no edits or redactions. Please be careful to not include confidential business or personal information, otherwise sensitive or protected information, or any information you do not wish to be posted.
A call for patent claims is included in the front matter of this draft. For additional information, see the Information Technology Laboratory (ITL) Patent Policy.
Direct questions to explainable-AI@nist.gov.
The comment period for this document is Aug. 17 through Oct. 15.
