# Evolution and BOPs * At unsupervised, we are really designing a "grid" via feature engineering, and then performing a constructed grid search via Pattern Find. We spend a good deal of time constructing this grid so that our grid search (PF) proves useful. * This seems to have a good deal of parallels with evolution. From pg. 222 Darwin's Dangerous Idea: > Adaptive evolution is a search process-driven by mutation, recombination, and selection-on fixed or deforming fitness landscapes. An adapting population flows over the landscape under these forces. The structure of such landscapes, smooth or rugged, governs both the evolvability of populations and the sustained fitness of their members. The structure of fitness landscapes inevitably imposes limitations on adaptive search. * Here, a fitness landscape is the environment in which an organism functions. Certain genomes and DNA will perform more effectively on this landscape. Mathematically, we can formalize this as: $f_E: \text{genome} \rightarrow \text{fitness score}$ Where $f_E$ is the *fitness function* of the *environment*, mapping a specific genome to a fitness score, based on performance in that environment. If the genome `ababbba` is *highly adapted* to the environment, $E$, then we may see: $f_E(\text{ababbba}) = maximum$ * How does this relate to BOPs? * Our environment is the grid that we are searching, similar to searching for specific strings of DNA in evolution. * In Evolution: Grid = DNA * In BOP: Grid = Combinations of Filter Sets *