mutual inhibition

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.

Mutual inhibition is when two or more neurones (artifical or biological) inhibit one another, that is when one being active makes the others less so. This can be direct nodes A and B each inhibit one another, or involve larger cycles, for example A inhibits B inhibits C inhibits A.. If the mutual inhibition is strong, this can lead to a 'winner takes all' situations, for example during disambiguation of an object in an image where, in the end, there is a single classification. Mutual inhibition can also lead to rhythmic behaviour, and can be found in the motor control of animals and insects.

Used on Chap. 6: pages 123, 124