Skip to main content
. 2020 Jan 17;13:1396. doi: 10.3389/fnins.2019.01396

Algorithm 3.

Evolution with Knowledge Transfer

Input: POP1, POP2, …, POPM, A1, A2, …, AM, δ (transfer interval)
Output: New Population and New Archives
 /* Preparation */
 t ← 1
 Generate initial M population randomly.
 Initialize M archive with corresponding population.
 /* Evolution */
 While ending condition not satisfied Do
      /* Searching */
      For each subpopulation POPi Do
          If t % δ = = 0 Then
              /* Transfer */
              krand(1, M)
              POPi ← Transfer(POPi, Ak)
          Else
              Self Evolution
      End For
      /* Updating */
      For each archive Ai Do
          Ai ← Update(POPi, Ai) as Algorithm 2
      End For
      tt + 1
 End While