4
$\begingroup$

I am looking a python lib named deap, but stuck at beginning.

The first paragraph says:

The problem is very simple, we search for a 1 filled list individual.

What does 1 filled list means? Search a 1 filled list, from where? individual list or individual 1?

Google One Max Problem only gives some information which seems to be useful:

  1. There is a Max One Problem

    I can understand this, but is it same as One Max Problem? If so, I have a question that why need evolutionary algorithm to "evolve" our population until eventually the target emerges. ? If I am a Medical Researcher, I should already have the entire DNA(gene list) , what I need to do is just search in that list, not evolve a random list.

  2. There is a Maximum_satisfiability_problem

    This is understandable too, seems relate to One Max Problem , another saying?

$\endgroup$
1
  • $\begingroup$ From your question about Medical Researcher and DNA, it looks like you are expecting to find a library that deals with genetic data of living creatures (you might want this to establish taxonomy or search for correlations between genes and another observation)? Instead you have a found a library that deals with optimisation problems by simulating core ideas from evolution. $\endgroup$ – Neil Slater Jan 12 '17 at 10:32
6
$\begingroup$

deap is an evolutionary algorithm library. In an evolutionary algorithm you usually want to optimize a function. For this, you define individuals as a collection of genes (e.g. a string of numbers) that condense a possible solution, you create a population of such individuals, and define a fitness function to evaluate how good they are; then you apply evolutionary operators (e.g. mutation, pairing) to evolve the population, effectively searching the solution space.

The problem referred to as "max one problem" in the linked page can be reworded as:

let's create a toy evolutionary algorithm where we want to evolve a population of individuals (where each individual is a list of N integer numbers) until one of them is exactly comprised of N ones (i.e. 1,1,....,1).

The "maximum satifiability problem" is not related to this.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.