Population variation in genetic programming

Applying a combined fuzzy systems and GARCH model to adaptively forecast stock market volatility

“…Mutation is the occasional flip of each bit of a chromosome from 1 to 0, or vice versa. Mutation should be used sparingly, as it is a random search operator; at high mutation rates, the algorithm degrades to a random search [18,23]. …”

“…. ., N sampled at equal sampling intervals, the standard problem is to construct a model and then to make one-step-ahead predictions to obtain the future value ofŷ(N + 1) [13,14,[22][23][24][25]. Many different algorithms allow us to evaluate the performance of the model.…”

An optimizing model to solve the nesting problem of rectangle pieces based on genetic algorithm

“…It will appear premature and stop at the immature stage when searching. Therefore, in order to avoid the premature convergence of the genetic algorithm, the population size cannot be too small in order to maintain the diversity of population, the general population size is usually between 20 and 100, if its value is too large or too small it would cause bad effect of the genetic algorithm (Alander 1992;Lane et al 2012;Kouchakpour et al 2007). …”

A genetic algorithm calibration method based on convergence due to genetic drift

“…Feedback based approaches such as these are not specific to the field of GAs. For example, population variation has been used for Genetic Programming [19], where the number of generations and fitness function values are used to control the population size, and minimize the computational effort required to find suitable solutions.…”