low-temperature search
An incremental search that makes small changes to a current solution to slightly improve fit to the data.
As defined in Alison Gopnik
Where it comes up · 1
- Alison Gopnik1 claim
Most important claims · 1 of 1Search all claims for “low-temperature search” →
- Learning resembles simulated annealing: a high-temperature search bounces randomly through the solution space trying wild ideas, while a low-temperature search makes small incremental changes; young children operate like high-temperature random search, whereas mature scientists must balance both, and big paradigm shifts come from improbable, high-temperature ideas.Alison Gopnik