Evolution Strategies (ESs) and Genetic Algorithms (GAs) are compared in a formal way. It is shown, that both algorithms are identical with respect to their major working scheme, but nevertheless they exhibit signiicant diierences with respect to the details of the selection scheme, the amount of the genetic representation and, especially, the self-adaptation of strategy parameters.

Generative adversarial networks (GANs) have proven successful in image generation tasks. However, GAN training is inherently unstable. Although many works try to stabilize it by manually modifying architecture, requires much expertise. Neural architecture search (NAS) has become an attractive solution GANs automatically. The early NAS-GANs only generators reduce complexity but lead a sub-optima...

The goals of this research were to search for Convolutional Neural Network (CNN) architectures, suitable an on-device processor with limited computing resources, performing at substantially lower Architecture Search (NAS) costs. A new algorithm entitled Early Exit Population Initialisation (EE-PI) Evolutionary Algorithm (EA) was developed achieve both goals. EE-PI reduces the total number param...

With the increase in number of optimization objectives, balancing convergence and diversity evolutionary multiobjective becomes more intractable. So far, a variety algorithms have been proposed to solve many-objective problems (MaOPs) with than three objectives. Most existing algorithms, however, find difficulties simultaneously counterpoising during whole process. To address issue, this paper ...

| For the calibration of laser induced plasma spectrometers robust and eecient local search methods are required. Therefore, several local optimizers from nonlinear optimization, random search and evolutionary computation are compared. It is shown that evolutionary algorithms are superior with respect to reliability and eeciency. To enhance the local search of an evolutionary algorithm a new me...