Stochastic selection algorithms

The uniform distribution stochastic selection algorithm is adopted to select the parent individuals... 

Table 5.9 shows how the number of copies of a set of strings may vary depending on the selection method chosen. Because each method contains a stochastic element, the values in the table would change if the algorithm was run a second time. 

Selecting the right variables often improves the models and makes interpretation easier. When there are too many descriptors, and especially when these descriptors do not have a clear physico-chemical meaning (e.g., connectivity indices and other 2D descriptors), stochastic methods such as genetic algorithms and evolutionary strategies can be used for finding an optimal subset of descriptors [91,92]. 

Linear Models. Variable selection approaches can be applied in combination with both linear and nonlinear optimization algorithms. Exhaustive analysis of all possible combinations of descriptor subsets to find a specific subset of variables that affords the best correlation with the target property is practically impossible because of the combinatorial nature of this problem. Thus, stochastic sampling approaches such as genetic or evolutionary algorithms (GA or EA) or simulated annealing (SA) are employed. To illustrate one such application we shall consider the GA-PLS method, which was implemented as follows (136). 

---