Results 11  20
of
77
Continuous interacting ant colony algorithm based on dense heterarchy
 Future Generation Computer Systems
"... Ant colony algorithms are a class of metaheuristics which are inspired from the behavior of real ants. The original idea consisted in simulating the stigmergic communication, therefore these algorithms are considered as a form of adaptive memory programming. A new formalization is proposed for the d ..."
Abstract

Cited by 14 (1 self)
 Add to MetaCart
Ant colony algorithms are a class of metaheuristics which are inspired from the behavior of real ants. The original idea consisted in simulating the stigmergic communication, therefore these algorithms are considered as a form of adaptive memory programming. A new formalization is proposed for the design of ant colony algorithms, introducing the biological notions of heterarchy and communication channels. We are interested in the way ant colonies handle the information. According to these issues, a heterarchical algorithm called “Continuous Interacting Ant Colony ” (CIAC) is designed for the optimization of multiminima continuous functions. CIAC uses two communication channels showing the properties of trail and direct communications. CIAC presents interesting emergent properties as it was shown through some analytical test functions.
Genetic Algorithms: What Fitness Scaling Is Optimal?
 Cybernetics and Systems: an International Journal
, 1993
"... . Genetic algorithms are now among the most promising optimization techniques. They are based on the following reasonable idea. Suppose that we want to maximize an objective function J(x). We somehow choose the first generation of "individuals" x 1 ; x 2 ; :::; x n (i.e., possible values of x) and c ..."
Abstract

Cited by 10 (5 self)
 Add to MetaCart
. Genetic algorithms are now among the most promising optimization techniques. They are based on the following reasonable idea. Suppose that we want to maximize an objective function J(x). We somehow choose the first generation of "individuals" x 1 ; x 2 ; :::; x n (i.e., possible values of x) and compute the "fitness" J(x i ) of all these individuals. To each individual x i , we assign a survival probability p i that is proportional to its fitness. In order to get the next generation we then repeat the following procedure k times: take two individuals at random (i.e., x i with probability p i ) and "combine" them according to some rule. For each individual of this new generation, we also compute its fitness (and survival probability), "combine" them to get the third generation, etc. Under certain reasonable conditions, the value of the objective function increases from generation to generation and converges to a maximal value. The performance of genetic algorithms can be essentially improved if we use fitness scaling, i.e., use f(J(x i )) instead of J(x i ) as a fitness value, where f(x) is some fixed function that is called a scaling function. The efficiency of fitness scaling essentially depends on the choice of f . So what f should we choose? In the present paper we formulate the problem of choosing f as a mathematical optimization problem and solve it under different optimality criteria. As a result, we get a list of functions f that are optimal under these criteria. This list includes both the functions that were empirically proved to be the best for some problems, and some new functions that may be worth trying. 1 1.
SelfAdaptation in Evolutionary Algorithms
 Parameter Setting in Evolutionary Algorithm
, 2006
"... this paper, we will give an overview over the selfadaptive behavior of evolutionary algorithms. We will start with a short overview over the historical development of adaptation mechanisms in evolutionary computation. In the following part, i.e., Section 2.2, we will introduce classification scheme ..."
Abstract

Cited by 10 (0 self)
 Add to MetaCart
this paper, we will give an overview over the selfadaptive behavior of evolutionary algorithms. We will start with a short overview over the historical development of adaptation mechanisms in evolutionary computation. In the following part, i.e., Section 2.2, we will introduce classification schemes that are used to group the various approaches. Afterwards, selfadaptive mechanisms will be considered. The overview is started by some examples  introducing selfadaptation of the strategy parameter and of the crossover operator. Several authors have pointed out that the concept of selfadaptation may be extended. Section 3.2 is devoted to such ideas. The mechanism of selfadaptation has been examined in various areas in order to find answers to the question under which conditions selfadaptation works and when it could fail. In the remaining sections, therefore, we present a short overview over some of the research done in this field
Identifying Component Modules
 Seventh International Conference on Artificial Intelligence in Design AID’02
, 2002
"... Abstract. A computerbased system for modelling component dependencies and identifying component modules is presented. A variation of the Dependency Structure Matrix (DSM) representation was used to model component dependencies. The system utilises a twostage approach towards facilitating the ident ..."
Abstract

Cited by 8 (1 self)
 Add to MetaCart
Abstract. A computerbased system for modelling component dependencies and identifying component modules is presented. A variation of the Dependency Structure Matrix (DSM) representation was used to model component dependencies. The system utilises a twostage approach towards facilitating the identification of a hierarchical modular structure. The first stage calculates a value for a clustering criterion that may be used to group component dependencies together. A Genetic Algorithm is described to optimise the order of the components within the DSM with the focus of minimising the value of the clustering criterion to identify the most significant component groupings (modules) within the product structure. The second stage utilises a ‘Module Strength Indicator’ (MSI) function to determine a value representative of the degree of modularity of the component groupings. The application of this function to the DSM produces a ‘Module Structure Matrix ’ (MSM) depicting the relative modularity of available component groupings within it. The approach enabled the identification of hierarchical modularity in the product structure without the requirement for any additional domain specific knowledge within the system. The system supports design by providing mechanisms to explicitly represent and utilise component and dependency knowledge to facilitate the nontrivial task of determining nearoptimal component modules and representing product modularity. 1.
Of metaphors and Darwinism: Deconstructing genetic programming's chimera
 Proceedings of the Congress on Evolutionary Computation
, 1999
"... This paper discusses several metaphors from Darwinism that have influenced the development of genetic programming (GP) theory. It specifically examines the historical lineage of these metaphors in evolutionary computation and their corresponding concepts in evolutionary biology and Darwinism. It id ..."
Abstract

Cited by 6 (0 self)
 Add to MetaCart
This paper discusses several metaphors from Darwinism that have influenced the development of genetic programming (GP) theory. It specifically examines the historical lineage of these metaphors in evolutionary computation and their corresponding concepts in evolutionary biology and Darwinism. It identifies problems that can arise from using these metaphors in the development of GP theory.
A Genetic Algorithm for Training Recurrent Neural Networks
, 1993
"... A hybrid genetic algorithm is proposed for training neural networks with recurrent connections. A fully connected recurrent ANN model is employed and tested over a number of various problems. Simulation results are presented for three problems: generation of a stable limit cycle, sequence recognitio ..."
Abstract

Cited by 6 (3 self)
 Add to MetaCart
A hybrid genetic algorithm is proposed for training neural networks with recurrent connections. A fully connected recurrent ANN model is employed and tested over a number of various problems. Simulation results are presented for three problems: generation of a stable limit cycle, sequence recognition and storage and reproduction of temporal sequences.
Automatic Feature Selection for Biological Shape Classification in Synergos
, 1998
"... This work reports the development of a versatile framework allowing the characterization and analysis of computer vision techniques as well as their applications to biological shapes, with attention focused on neural cells. The proposed framework has been implemented within the Synergos system, a po ..."
Abstract

Cited by 6 (2 self)
 Add to MetaCart
This work reports the development of a versatile framework allowing the characterization and analysis of computer vision techniques as well as their applications to biological shapes, with attention focused on neural cells. The proposed framework has been implemented within the Synergos system, a powerful imaging laboratory that includes, among other features, tools for performance assessment of computer vision techniques, image databases, realtime processing by using distributed systems and interface with the Internet. The motivations for the development of such a framework: (i) the importance of biological shape analysis; (ii) its potential as an effective tool for the systematic assessment of image processing and analysis techniques; and (iii) the possibility of conducting extensive characterizations of biological shapes. The paper describes an experiment to assess multiscale shape features for complexity characterization, which have been adopted for the classification of two types of ganglion neural cells (cat), namely a and b. This experiment involves: (1) a training stage where the kmeans clustering algorithm learns the prototypes of each class from the database; (2) the neurons in the database are classified; (3) the classification results are compared to the original classes; and (4) the number of misclassifications is determined. The genetic algorithm is used as a means of effectively investigating the Ndimensional spaces defined by the parameter configurations.
The Existential Pleasures of Genetic Algorithms
 Cuesta (Eds), Genetic Algorithms in Engineering and Computer Science
, 1994
"... this article, I make the same two points about genetic algorithms (GAs)that GAs are multifacetted and funand I believe the analogy I am drawing is a fairly tight one if it is viewed in the following way. The world employs both engineering and genetic algorithms for what they can dothe exter ..."
Abstract

Cited by 5 (0 self)
 Add to MetaCart
this article, I make the same two points about genetic algorithms (GAs)that GAs are multifacetted and funand I believe the analogy I am drawing is a fairly tight one if it is viewed in the following way. The world employs both engineering and genetic algorithms for what they can dothe external interest in the two subjects is almost always utilitarianand both engineers and genetic algorithmists themselves take great pride in what they can
Geographical Optimization using Evolutionary Algorithms
, 2003
"... During the last two decades, evolutionary algorithms (EAs) have been applied to a wide range of optimization and decisionmaking problems. Work on EAs for geographic analysis, however, has been conducted in a problemspecific manner, which prevents an EA designed for one type of problem to be used o ..."
Abstract

Cited by 5 (0 self)
 Add to MetaCart
During the last two decades, evolutionary algorithms (EAs) have been applied to a wide range of optimization and decisionmaking problems. Work on EAs for geographic analysis, however, has been conducted in a problemspecific manner, which prevents an EA designed for one type of problem to be used on others. The purpose of this paper is to describe a framework that unifies the design and implementation of EAs for different types of geographic optimization problems. The key element in this framework is a graph representation that can be used to formally define the spatial structure of a broad range of geographic problems. Based on this representation, spatial constraints (e.g., contiguity and adjacency) of optimization problems can be effectively maintained, and general principles of designing evolutionary algorithms for geographic optimization are identified. The framework is applied to an example political redistricting problem. 1
Modeling Genetic Algorithms with Interacting Particle Systems
 In Theoretical Aspects of Evolutionary Computing
, 2001
"... We present in this work a natural Interacting Particle System (IPS) approach for modeling and studying the asymptotic behavior of Genetic Algorithms (GAs). In this model, a population is seen as a distribution (or measure) on the search space, and the Genetic Algorithm as a measure valued dynamical ..."
Abstract

Cited by 5 (0 self)
 Add to MetaCart
We present in this work a natural Interacting Particle System (IPS) approach for modeling and studying the asymptotic behavior of Genetic Algorithms (GAs). In this model, a population is seen as a distribution (or measure) on the search space, and the Genetic Algorithm as a measure valued dynamical system. This model allows one to apply recent convergence results from the IPS literature for studying the convergence of genetic algorithms when the size of the population tends to infinity. We first review a number of approaches to Genetic Algorithms modeling and related convergence results. We then describe a general and abstract discrete time Interacting Particle System model for GAs, an we propose a brief review of some recent asymptotic results about the convergence of the NIPS approximating model (of finite Nsizedpopulation GAs) towards the IPS model (of infinite population GAs), including law of large number theorems, IL p mean and exponential bounds as well as large deviations...