Anne Defaweux

Transition models as an incremental approach for problem solving in evolutionary algorithms

This paper proposes an incremental approach for building solutions using evolutionary computation. It presents a simple evolutionary model called a Transition model in which partial solutions are constructed that interact to provide larger solutions. An evolutionary process is used to merge these partial solutions into a full solution for the problem at hand. The paper provides a preliminary study on the evolutionary dynamics of this model as well as an empirical comparison with other evolutionary techniques on binary constraint satisfaction.

Evolutionary transitions as a metaphor for evolutionary optimisation

This paper proposes a computational model for solving optimisation problems that mimics the principle of evolutionary transitions in individual complexity. More specifically it incorporates mechanisms for the emergence of increasingly complex individuals from the interaction of more simple ones. The biological principles for transition are outlined and mapped onto an evolutionary computation context. The class of binary constraint satisfaction problems is used to illustrate the transition mechanism.

Developmental effects on tuneable fitness landscapes

Due to the scalability issue in genetic algorithms there is a growing interest in adopting development as a genotype-phenotype mapping. This raises a number of questions related to the evolutionary and developmental properties of the genotypes in this context. This paper introduces the NK-development (NKd) class of tuneable fitness landscapes as a variant of NK landscapes. In a first part the assumptions and choices made in defining a simplified model of development genomes are discussed. In a second part we present results of the comparison of NK and two variants of NKd landscapes. The statistical properties of the landscapes are analysed, and the performance of a standard GA on the different landscapes is compared. The analysis is aimed at identifying the influence of the properties by which the landscapes differ. The results and their implications for the design of computational development models are discussed.

Linear genetic programming using a compressed genotype representation

This paper presents a modularization strategy for linear genetic programming (GP) based on a substring compression/substitution scheme. The purpose of this substitution scheme is to protect building blocks and is in other words a form of learning linkage. The compression of the genotype provides both a protection mechanism and a form of genetic code reuse. This paper presents results for synthetic genetic algorithm (GA) reference problems like SEQ and OneMax as well as several standard GP problems. These include a real world application of GP to data compression. Results show that despite the fact that the compression substrings assumes a tight linkage between alleles, this approach improves the search process.

Solving Hierarchically Decomposable Problems with the Evolutionary Transition Algorithm

Capturing the metaphor of evolutionary transitions in biological complexity, the Evolutionary Transition Algorithm (ETA) evolves solutions of increasing structural and functional complexity from the symbiotic interaction of partial ones. From the definition it follows that this algorithm should be very well suited to solve hierarchically decomposable problems. In this chapter, we show that the ETA can indeed solve this kind of problems effectively.We analyze, in depth, its behavior on hierarchical problems of different size and modular complexity. These results are compared to the Symbiogenetic Model and it is shown that the ETA is more robust and efficient to tackle this kind of problems.

The Evolutionary Transition Algorithm: Evolving Complex Solutions Out of Simpler Ones

Capturing the metaphor of evolutionary transitions in biological complexity, the Evolutionary Transition Algorithm (ETA) evolves solutions of increasing structural and functional complexity from the symbiotic interaction of partial ones. In this chapter we show that the ETA indeed captures this idea and we illustrate this on instances of the Binary Constraint Satisfaction problem. The results make the ETA a promising optimization approach that requires more extensive investigation from both a theoretical and optimization perspective. We analyze here, in depth, some of the design choices that are made for the algorithm. The analysis of these choices provides insight on the plasticity of the algorithm toward alternative choices and other kinds of problems.

Transitions in a Simple Evolutionary Model

We report on the construction of a simple alife model to invesitgate the theories concerning evolutionary transitions. These theories can be considered as biological metaphors for cooperative problem solving. The benefit of this model for computer science results from the models property to assimilate, in evolutionary fashion, complex structures from simple ones. It is this assimilation process we want to capture in an algorithm in order to apply it to learning and optimization problems.