Immune Memory

After the process of proliferation and hyper-mutation, the elements enhanced in clonal pool or progenies are evaluated for their antigenic affinity. As per to the Clonal theory, instead of keeping a large number of candidate solutions, a minute set of high affinity antibodies are kept in the immune memory. We employ the immune memory like an elitist mechanism in order to maintain the best solutions found along the process. It is a very significant characteristic of IAS and makes sure that candidate solutions along with high fitness value will be preserved.

The secondary memory conserves the high affinity antibodies in the clonal pool for making the next generation population. This makes sure faster convergence or and fewer entrapments in local minima.

The common steps for this strategy is detailed in described procedure:

Procedure: Function of Immune Memory in Generation t.

Parameters: m = Immune memory population size,

Ps = Population size,

t = current iteration 

Parameters: (IM)^t_m= Immune Memory at t^th iteration,

d = update lower bound,

Parameters: (P)^t_Ps = population at t^th iteration,+ = 0! = 1

Begin

(IM)^t_m= update (IM) _m ^t-1

μ = No. of new antibodies in (IM)^t_m

 if (μ > d)

(P)^t_Ps = μ best current Antibodies, and (Ps - μ) Random antibodies

 Else,

X = ((P)^t_Ps)/ (1 + log(+))

P)^t_Ps  = χ Antibodies from (IM)^t_m

 And (Ps - χ ) Random Antibodies

Γ = Γ + 1

end

end if

From above step this is evident that if the Immune memory or IM update is greater than a specific limit, then best antibodies of recent generation are selected to kept search direction. If the update criterion is not fulfilled then we go for the best antibodies stored in immune memory into exploit the search space extra effectively and to escape from local minima. Notice that in the immune memory, the selection is completed by employing the roulette wheel selection rule.