Solving optimization problems with multiple (often conflicting) objectives is, generally, a very difficult goal. Evolutionary algorithms (EAs) were initially extended and applied during the mid-eighties in an attempt to stochastically solve problems of this generic class. During the past decade, a variety of multiobjective EA (MOEA) techniques have been proposed and applied to many scientific and engineering applications. Our discussion's intent is to rigorously define multiobjective optimization problems and certain related concepts, present an MOEA classification scheme, and evaluate the variety of contemporary MOEAs. Current MOEA theoretical developments are evaluated; specific topics addressed include fitness functions, Pareto ranking, niching, fitness sharing, mating restriction, and secondary populations. Since the development and application of MOEAs is a dynamic and rapidly growing activity, we focus on key analytical insights based upon critical MOEA evaluation of c...

This paper provides a comprehensive survey of the most popular constraint-handling techniques currently used with evolutionary algorithms. We review approaches that go from simple variations of a penalty function, to others, more sophisticated, that are biologically inspired on emulations of the immune system, culture or ant colonies. Besides describing briefly each of these approaches (or groups of techniques), we provide some criticism regarding their highlights and drawbacks. A small comparative study is also conducted, in order to assess the performance of several penalty-based approaches with respect to a dominance-based technique proposed by the author, and with respect to some mathematical programming approaches. Finally, we provide some guidelines regarding how to select the most appropriate constraint-handling technique for a certain application, ad we conclude with some of the the most promising paths of future research in this area.

this article is to introduce the ideas and methods of reliability theory to a wider audience interested in understanding the mechanisms of aging, mortality, survival, and longevity. It is also important to review and summarize the recent scienti"c literature on reliability approach to the problem of biological aging (Miller, 1989; Gavrilov & Gavrilova, 1991; Abernethy, 1998; Bains, 2000). The main emphasis here is made on the accomplishments of the reliability approach rather than previous occasional mistakes, because some questionable models (Murphy, 1978; Skurnick & Kemeny, 1978; Koltover, 1983, 1997; Witten, 1985) were already reviewed elsewhere (Gavrilov, 1984, 1987; Gavrilov & Gavrilova, 1991). This theoretical review article also elaborates further some results and ideas published in the book on a related topic (Gavrilov & Gavrilova, 1991)

Abstract. A new class of evolutionary computation processes is presented, called Learnable Evolution Model or LEM. In contrast to Darwinian-type evolution that relies on mutation, recombination, and selection operators, LEM employs machine learning to generate new populations. Specifically, in Machine Learning mode, a learning system seeks reasons why certain individuals in a population (or a collection of past populations) are superior to others in performing a designated class of tasks. These reasons, expressed as inductive hypotheses, are used to generate new populations. A remarkable property of LEM is that it is capable of quantum leaps (“insight jumps”) of the fitness function, unlike Darwinian-type evolution that typically proceeds through numerous slight improvements. In our early experimental studies, LEM significantly outperformed evolutionary computation methods used in the experiments, sometimes achieving speed-ups of two or more orders of magnitude in terms of the number of evolutionary steps. LEM has a potential for a wide range of applications, in particular, in such domains as complex optimization or search problems, engineering design, drug design, evolvable hardware, software engineering, economics, data mining, and automatic programming.

Abstract not found

We present an alternative to standard genetic programming (GP) that applies layered learning techniques to decompose a problem. GP is applied to subproblems sequentially, where the population in the last generation of a subproblem is used as the initial population of the next subproblem. This method is applied to evolve agents to play keep-away soccer, a subproblem of robotic soccer that requires cooperation among multiple agents in a dynamic environment. The layered learning paradigm allows GP to evolve better solutions faster than standard GP. Results show that the layered learning GP outperforms standard GP by evolving a lower tness faster and an overall better tness. Results indicate a wide area of future research with layered learning in GP.

Abstract not found

Since the demonstration, in 1998, of the phenomenon now widely known as ‘fishing down marine food webs’, and the publication of a critical rejoinder by Food and Agricultural Organization (FAO) staff, a number of studies have been conducted in different parts of the world, based on more detailed data than the global FAO fisheries statistics originally used, which established the validity and ubiquity of this phenomenon. In this contribution, we briefly review how, rather than being an artefact of biased data, this phenomenon was in fact largely masked by such data, and is in fact more widespread than was initially anticipated. This is made visible here by comparing two global maps of trophic level (TL) changes from the early 1950s to the present. The first presents the 50-year difference of the grand mean TL values originally used to demonstrate the fishing down effect, while the second is based on means above a cut-off TL (here set at 3.25), thus eliminating the highly variable and abundant small pelagic fishes caught throughout the world. Based on this, we suggest that using mean TL as ‘Marine Trophic Index ’ (MTI), as endorsed by the Convention on Biological Diversity, always be done with an explicitly stated cut-off TL (i.e. cut MTI), chosen (as is the case with our proposed value of 3.25) to emphasize changes in the relative abundance of the more threatened, high-TL fishes. We also point out the need to improve the taxonomic resolution, completeness and accuracy of the national and international fisheries catch data series upon which the cut MTI is to be based.

It is remarkable to think that even without any interest in finding suitable methods and concepts that would allow complex software systems to evolve and remain manageable, the ever growing open source movement has silently managed to establish highly successful evolution techniques over the last two decades. These concepts represent best practices that could be applied equally to a number of today 's most crucial problems concerning the evolution of complex commercial software systems. In this paper, the authors state and explain some of these principles from the perspective of experienced open source developers, and give the rationale as to why the highly dynamic "free software development process", as a whole, is entangled with constantly growing code bases and changing project sizes, and how it deals with these successfully.

Despite its current popularity, “emergence” is a concept with a venerable history and an elusive, ambiguous standing in contemporary evolutionary theory. This paper briefly recounts the history of the term and details some of its current usages. Not only are there radically varying interpretations about what emergence means but “reductionist ” and “holistic ” theorists have very different views about the issue of causation. However, these two seemingly polar positions are not irreconcilable. Reductionism, or detailed analysis of the parts and their interactions, is essential for answering the “how ” question in evolution--how does a complex living system work? But holism is equally necessary for answering the “why ” question-- why did a particular arrangement of parts evolve? In order to answer the “why ” question, a broader, multi-leveled paradigm is required. The reductionist approach to explaining emergent complexity has entailed a search for underlying “laws of emergence.” Another alternative is the “Synergism Hypothesis, ” which focuses on the “economics ” – the functional effects produced by emergent wholes and their selective consequences. This theory, in a nutshell, proposes that the synergistic (co-operative) effects produced by various combinations of parts have played a major causal role in the evolution of biological complexity. It will also be argued that emergent phenomena represent, in effect, a subset of a much larger universe of combined effects in the natural world; there are many different kinds of synergy, but not all synergies represent emergent phenomena.