related. I am confident that at their interface great discoveries await those who seek them. ” (L.Adleman, [3]) 1. FOREWORD Natural computing is the field of research that investigates models and computational techniques inspired by nature and, dually, attempts to understand the world around us in terms of information processing. It is a highly interdisciplinary field that connects the natural sciences with computing science, both at the level of information technology and at the level of fundamental research, [98]. As a matter of fact, natural computing areas and topics come in many flavours, including pure theoretical research, algorithms and software applications, as well as biology, chemistry and physics experimental laboratory research. In this review we describe computing paradigms abstracted

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 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.

Abstract. A computer-based 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 two-stage 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 near-optimal component modules and representing product modularity. 1.

this paper, we will give an overview over the self-adaptive 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, self-adaptive mechanisms will be considered. The overview is started by some examples -- introducing self-adaptation of the strategy parameter and of the crossover operator. Several authors have pointed out that the concept of self-adaptation 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 self-adaptation 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

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, real-time 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 k-means 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 N-dimensional spaces defined by the parameter configurations.

This article provides over one hundred references to works in the medical domain using evolutionary computation

this article, I make the same two points about genetic algorithms (GAs)---that GAs are multifacetted and fun---and 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 do---the external interest in the two subjects is almost always utilitarian---and both engineers and genetic algorithmists themselves take great pride in what they can

Abstract. The search for similar configurations is an important research topic for content-based image retrieval in G.I.S. and spatial databases. Due to the complexity of the problem, finding the fittest solution in a large database is computationally intractable. Our work is focused on designing, implementing and experimentally evaluating two heuristic algorithms, an evolutionary and a hill-climbing one, that provide an approximate solution. With the use of spatial indexes we manage to efficiently deal with considerably large queries. We utilize a similarity framework that addresses topological, directional and distance relations. In this framework the problem of retrieving similar configurations is defined as a binary constraint satisfaction problem. Our work complements the existing work on similarity retrieval with two efficient, stochastic, algorithms. 1

Both genetic algorithms and neural networks are machine learning techniques inspired by nature. By mimicking, although in a simplied way, biological processes, new alternatives in problem solving can be explored. We are interested in the application of these strategies in the eld of natural language processing. Here we provide an overview of previously published material in this area. We trace which domains of natural language processing have been investigated with evolutionary or neural strategies, discuss approaches and experiments, and provide an introduction to the literature. 1 Introduction Both evolutionary algorithms and articial neural networks mimick aspects of biological processes. In this section we introduce these methods and point to the general literature. 1.1 Evolutionary Computing The idea of using evolutionary computation as a problem solving technique exists since the 1950s (Box, 1957), (Bledsoe, 1961), (Fraser, 1957). Since then, four major approaches ha...