Abstract. In recent years dynamic optimization problems have attracted a growing interest from the community of genetic algorithms with several approaches developed to address these problems, of which the memory scheme is a major one. In this paper an associative memory scheme is proposed for genetic algorithms to enhance their performance in dynamic environments. In this memory scheme, the environmental information is also stored and associated with current best individual of the population in the memory. When the environment changes the stored environmental information that is associated with the best re-evaluated memory solution is extracted to create new individuals into the population. Based on a series of systematically constructed dynamic test environments, experiments are carried out to validate the proposed associative memory scheme. The environmental results show the efficiency of the associative memory scheme for genetic algorithms in dynamic environments. 1

Abstract- Several approaches have been developed into evolutionary algorithms to deal with dynamic optimization problems, of which memory and random immigrants are two major schemes. This paper investigates the application of a direct memory scheme for univariate marginal distribution algorithms (UMDAs), a class of evolutionary algorithms, for dynamic optimization problems. The interaction between memory and random immigrants for UMDAs in dynamic environments is also investigated. Experimental study shows that the memory scheme is efficient for UMDAs in dynamic environments and that the interactive effect between memory and random immigrants for UMDAs in dynamic environments depends on the dynamic environments. 1

In recent years the genetic algorithm community has shown a growing interest in studying dynamic optimization problems. Several approaches have been devised. The random immigrants and memory schemes are two major ones. The random immigrants scheme addresses dynamic environments by maintaining the population diversity while the memory scheme aims to adapt genetic algorithms quickly to new environments by reusing historical information. This paper investigates a hybrid memory and random immigrants scheme, called memory-based immigrants, and a hybrid elitism and random immigrants scheme, called elitism-based immigrants, for genetic algorithms in dynamic environments. In these schemes, the best individual from memory or the elite from the previous generation is retrieved as the base to create immigrants into the population by mutation. This way, not only can diversity be maintained but it is done more efficiently to adapt genetic algorithms to the current environment. Based on a series of systematically constructed dynamic problems, experiments are carried out to compare genetic algorithms with the memory-based and elitism-based immigrants schemes against genetic algorithms with traditional memory and random immigrants schemes and a hybrid memory and multi-population scheme. The sensitivity analysis regarding some key parameters is also carried out. Experimental results show that the memory-based and elitism-based immigrants schemes efficiently improve the performance of genetic algorithms in dynamic environments.

Diversity and memory are two major mechanisms used in biology to keep the adaptability of organisms in the everchanging environment in nature. These mechanisms can be integrated into genetic algorithms to enhance their performance for problem optimization in dynamic environments. This paper investigates several GAs inspired by the ideas of biological immune system and transformation schemes for dynamic optimization problems. An aligned transformation operator is proposed and combined to the immune system based genetic algorithm to deal with dynamic environments. Using a series of systematically constructed dynamic test problems, experiments are carried out to compare several immune system based genetic algorithms, including the proposed one, and two standard genetic algorithms enhanced with memory and random immigrants respectively. The experimental results validate the efficiency of the proposed aligned transformation and corresponding immune system based genetic algorithm in dynamic environments.

Abstract. There has been a growing interest in studying evolutionary algorithms in dynamic environments in recent years due to its importance in real applications. However, different dynamic test problems have been used to test and compare the performance of algorithms. This paper proposes a generalized dynamic benchmark generator (GDBG) that can be instantiated into the binary space, real space and combinatorial space. This generator can present a set of different properties to test algorithms by tuning some control parameters. Some experiments are carried out on the real space to study the performance of the generator. 1

Abstract. This paper proposes a memory scheme based on abstraction for evolutionary algorithms to address dynamic optimization problems. In this memory scheme, the memory does not store good solutions as themselves but as their abstraction, i.e., their approximate location in the search space. When the environment changes, the stored abstraction information is extracted to generate new individuals into the population. Experiments are carried out to validate the abstraction based memory scheme. The results show the efficiency of the abstraction based memory scheme for evolutionary algorithms in dynamic environments. 1

The present dissertation would have never been achieved without the support of a variety of people. I am particularly indebted to Jose Antonio Lozano, my thesis supervisor. Undoubtedly, his wise, while at the same time friendly guidance throughout these years has made me grow a lot. Jose Antonio, thanks for your invaluable help and patience. I am also grateful to Pedro Larrañaga, Iñaki Inza, Alex Mendiburu, Endika Bengoetxea and the rest of my colleagues at the Intelligent Systems Group. Their encouragement and advice have been decisive as well. I would like to make special mention of my lab

Abstract. Adaptation to dynamic optimization problems is currently receiving a growing interest as one of the most important applications of evolutionary algorithms. In this paper, a compound particle swarm optimization (CPSO) is proposed as a new variant of particle swarm optimization to enhance its performance in dynamic environments. Within CPSO, compound particles are constructed as a novel type of particles in the search space and their motions are integrated into the swarm. A special reflection scheme is introduced in order to explore the search space more comprehensively. Furthermore, some information preserving and anti-convergence strategies are also developed to improve the performance of CPSO in a new environment. An experimental study shows the efficiency of CPSO in dynamic environments. 1

Abstract Dynamic optimization problems challenge traditional evolutionary algorithms seriously since they, once converged, cannot adapt quickly to environmental changes. This paper investigates the application of memetic algorithms, a class of hybrid evolutionary algorithms, for dynamic optimization problems. An adaptive hill climbingmethodisproposedasthe localsearchtechnique in the framework of memetic algorithms, which combinesthefeaturesofgreedycrossover-basedhillclimbing and steepest mutation-based hill climbing. In order to address the convergence problem, two diversity maintaining methods, called adaptive dual mapping and triggered random immigrants respectively, are also introduced into the proposed memetic algorithm for dynamic optimization problems. Based on a series of dynamic problems generated from several stationary benchmark problems, experiments are carried out to investigate the performance of the proposed memetic algorithm in comparisonwith some peer evolutionaryalgorithms.The experimental results show the efficiency of the proposed memetic algorithm in dynamic environments. Keywords Geneticalgorithm,memeticalgorithm,local search,crossover-basedhill climbing, mutation-based hill climbing, dual mapping, triggered random immigrants, dynamic optimization problems 1

Abstract—Depth information using the biological Disparity Energy Model can be obtained by using a population of complex cells. This model explicitly involves cell parameters like their spatial frequency, orientation, binocular phase and position difference. However, this is a mathematical model. Our brain does not have access to such parameters, it can only exploit responses. Therefore, we use a new model for encoding disparity information implicitly by employing a trained binocular neuronal population. This model allows to decode disparity information in a way similar to how our visual system could have developed this ability, during evolution, in order to accurately estimate disparity of entire scenes. Keywords—disparity, population coding, learning, biological model I.