Niching methods extend genetic algorithms to domains that require the location and maintenance of multiple solutions. Such domains include classification and machine learning, multimodal function optimization, multiobjective function optimization, and simulation of complex and adaptive systems. This study presents a comprehensive treatment of niching methods and the related topic of population diversity. Its purpose is to analyze existing niching methods and to design improved niching methods. To achieve this purpose, it first develops a general framework for the modelling of niching methods, and then applies this framework to construct models of individual niching methods, specifically crowding and sharing methods. Using a constructed model of crowding, this study determines why crowding methods over the last two decades have not made effective niching methods. A series of tests and design modifications results in the development of a highly effective form of crowding, called determin...

The success of binary-coded genetic algorithms (GAs) in problems having discrete search space largely depends on the coding used to represent the problem variables and on the crossover operator that propagates building-blocks from parent strings to children strings. In solving optimization problems having continuous search space, binary-coded GAs discretize the search space by using a coding of the problem variables in binary strings. However, the coding of real-valued variables in finite-length strings causes a number of difficulties---inability to achieve arbitrary precision in the obtained solution, fixed mapping of problem variables, inherent Hamming cliff problem associated with the binary coding, and processing of Holland's schemata in continuous search space. Although, a number of real-coded GAs are developed to solve optimization problems having a continuous search space, the search powers of these crossover operators are not adequate. In this paper, the search power of a cross...

The conventional understanding of genetic algorithms depends upon analysis by schemata and the notion of intrinsic parallelism. For this reason, only k-ary string representations have had any formal basis and non-standard representations and operators have been regarded largely as heuristics, rather than principled algorithms. This paper extends the analysis to general representations through identification of schemata as equivalence classes induced by implicit equivalence relations over the space of chromosomes.

. Genetic algorithms play a significant role, as search techniques for handling complex spaces, in many fields such as artificial intelligence, engineering, robotic, etc. Genetic algorithms are based on the underlying genetic process in biological organisms and on the natural evolution principles of populations. These algorithms process a population of chromosomes, which represent search space solutions, with three operations: selection, crossover and mutation. Under its initial formulation, the search space solutions are coded using the binary alphabet. However, the good properties related with these algorithms do not stem from the use of this alphabet; other coding types have been considered for the representation issue, such as real coding, which would seem particularly natural when tackling optimization problems of parameters with variables in continuous domains. In this paper we review the features of real-coded genetic algorithms. Different models of genetic operators and some me...

A central problem in the theory of genetic algorithms is the characterization of problems that are difficult for GAs to optimize. Many attempts to characterize such problems focus on the notion of Deception, defined in terms of the static average fitness of competing schemas. This article examines the Static Building Block Hypothesis (SBBH), the underlying assumption used to define Deception. Exploiting contradictions between the SBBH and the Schema Theorem, we show that Deception is neither necessary nor sufficient for problems to be difficult for GAs. This article argues that the characterization of hard problems must take into account the basic features of genetic algorithms, especially their dynamic, biased sampling strategy. Keywords: Deception, building block hypothesis 1 INTRODUCTION Since Holland's early work on the analysis of genetic algorithms (GAs), the usual approach has been to focus on the allocation of search effort to subspaces described by schemas representing hyper...

Forma analysis is applied to the task of optimising the connectivity of a feed-forward neural network with a single layer of hidden units. This problem is reformulated as a multiset optimisation problem and techniques are developed to allow principled genetic search over fixed- and variable-size sets and multisets. These techniques require a further generalisation of the notion of gene, which is presented. The result is a non-redundant representation of the neural network topology optimisation problem together with recombination operators which have carefully designed and well-understood properties. The techniques developed have relevance to the application of genetic algorithms to constrained optimisation problems.

Self-adaptation is an essential feature of natural evolution. However, in the context of function optimization, self-adaptation features of evolutionary search algorithms have been explored only with evolution strategy (ES) and evolutionary programming (EP). In this paper, we demonstrate the selfadaptive feature of real-parameter genetic algorithms (GAs) using simulated binary crossover (SBX) operator and without any mutation operator. The connection between the working of self-adaptive ESs and real-parameter GAs with SBX operator is also discussed. Thereafter, the self-adaptive behavior of real-parameter GAs is demonstrated on a number of test problems commonly-used in the ES literature. The remarkable similarity in the working principle of real-parameter GAs and self-adaptive ESs shown in this study suggests the need of emphasizing further studies on self-adaptive GAs.

This paper develops a framework for optimizing global-local hybrids of search or optimization procedures. The paper starts by idealizing the search problem as a search by a global algorithm G for either (1) acceptable targets|solutions that meet a speci ed criterion|or for (2) basins of attraction that then lead to acceptable targets under a speci ed local search algorithm L. The paper continues by abstracting two sets of parameters|probabilities of successfully hitting targets and basins and time-to-criterion coe cients|and writing equations to account for the total time of search and for the reliability in reaching an acceptable solution. A two-basin optimality criterion is derived and applied to important representative problems. Continuations and extensions of the work are suggested, but the theory appears to be useful immediately in better understanding the economy of e ective hybridization. 1

The limitations of linear chromosomes and conventional recombination operators are reviewed. It is argued that there are at least three classes of problems for which such representations and operators are likely to be ineffective. Methods for constructing operators which manipulate more complex structures with evolutionary search methods are presented, and it is argued that whenever possible, genetic operators and analogues of schemata should be defined directly in space of phenotypes, rather than in the genotype (representation) space.

In this paper, we use a genetic algorithm to evolve a set of classification rules with real-valued attributes. We show how real-valued attribute ranges can be encoded with real-valued genes and present a new uniform method for representing don't cares in the rules. We view supervised classification as an optimization problem, and evolve rule sets that maximize the number of correct classifications of input instances. We use a variant of the Pitt approach to genetic-based machine learning system with a novel conflict resolution mechanism between competing rules within the same rule set. Experimental results demonstrate the effectiveness of our proposed approach on a benchmark wine classifier system. I. Introduction Genetic algorithms (GAs) have proved to be robust, domain independent mechanisms for numeric and symbolic optimization[7]. Our previous work has demonstrated effective genetic-based rule learning in discrete domains [13]. In the real world, however, most classification prob...