threshold

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 threshold is a critical value beyond which some event occurs or values change drastically. In biological neorones and artificial neurons there is often no reaction for small or moderate amounts of activation from other neorons. However, if the level of input activation goes beyond some threshold, then the neuron will fully fire.

Defined on page 246

Used on Chap. 6: pages 110, 114, 115, 116, 120; Chap. 9: pages 180, 181, 192, 193; Chap. 10: pages 204, 205; Chap. 12: pages 246, 248, 249, 250, 253, 255, 259, 260, 261, 262, 269, 276, 286; Chap. 19: page 481; Chap. 20: page 490; Chap. 21: page 523

Also known as thresholding