clarity (knowledge representation)

Terms from Artificial Intelligence: humans at the heart of algorithms

Page numbers are for draft copy at present; they will be replaced with correct numbers when final book is formatted. Chapter numbers are correct and will not change now.

A knowledge representation has clarity if it can be understood by knowledge engineers and ideally also by domain experts. In some cases, even if he underlying representation is opaque (for example neural networks or statistical technques applied to big data, it may be possible to use methods of explainable AI to give more clarity. Clarity is one of the facets of expressiveness.

Used in Chap. 2: page 14