A technique which can be applied to any minimisation or learning process based on successive update steps (either random or href="module.php?name=Lexikon&file=search&eid=1&query=deterministic">deterministic) where the update step length is proportional to an arbitrarily set parameter which can play the role of a temperature. Then, in analogy with the annealing of metals, the temperature is made high in the early stages of the process for faster minimisation or learning, then is reduced for greater stability.