Operators:
Same like in genetics, the best solutions are combined or/and suffer mutations in such way that the "genetic material" to be the best. From here a new population of solutions are created(new wiser advisors) and those come up with another set of solutions better than the first ones. And the process goes again to Hierarchy=>Selection=>Operators=>Offspring
This process lead in the end to a number of feasible solutions made from genes(data) but with new optimized parameters.
Modeling Problem's Space:
Problem's Space is limited by the Objective Functions f(min|max) - objectives that must be optimized- no matter its number f1(min|max), f2(min|max), f3(min|max)… fn(min|max) and restrictions R(R1,R2,R3,…Rn) no matter its number(which lead us to a multi dimensional space)
Genes selection:
Genes represent actual data of the process that must be optimized whatever would be that process. Please note that doesn't matter the number of them.
Initial population:
Once the problem space is created, and the genes are define, next step is to create a population(number of solutions) starting from genes(actual data). This process is like from the start we have a lot on "specialist advisors) and each advisor come up with its own solution over whatever that problem is.
Hierarchy and selection of the best Solutions:
Each solution in part is to be analyzed and hierarchically added in such way that in the end the best solution are selected(same like Darwin natural selection theory- The Best, survive).
