top-down reasoning

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.

Top-down reasoning begins with goals, context and other high-level constructs and working down towarsd the low-level sensing and data. For example means–ends analysis starts off with a goal and then works put sub-goals that if successful would enable the goal. In reality most systems needa combination of top-down and bottom-up reasoning. For example, in natural language processing expectations of what are likely to be topics of conversation can be fed down into lower levels, for example as probabiliities or vocabulary items, (top down), and can then be used by lower-level processes as they disambiguate words in speech-to-text ready for grammatical parsing (bottom up).

Used in Chap. 3: page 28

Also known as top-down