learning rate

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.

The learning rate is the speed with which the fitness function improves during an iterative algorithm, for example hill climbing. Typically, the fitness improves rapidly during the first few iterations, but this rate slows as the algorithm continues. As the alorithm approaches the optimal value the learning rates gets very slow, however, this can also be a sign of a plateau or local maxima in the fitness landscape.

Used in Chap. 9: page 133