Creative products are generally recognised as satisfying two requirements: firstly they are useful, and secondly they are novel. Much effort in AI and design computing has been put into developing systems that can recognise the usefulness of the products that they generate. In contrast, the work presented in this thesis has concentrated on developing computational systems that are able to recognise the novelty of their work. The research has shown that when computational systems are given the ability to recognise both the novelty and the usefulness of their products they gain a level of autonomy that opens up new possibilities for the study of creative behaviour in single agents and the emergence of social creativity in multi-agent systems. The work

This paper reviews five popular selection methods used in EAs. The algorithms are examined using the cumulants of the fitness distribution of the selected individuals. The cumulants are calculated using order statistics. The method presented here considers finite populations of arbitrary size. The results show important differences among the selection methods considered, even when they are configured to have the same selection intensity.

Genetic algorithms (GAs) that solve hard problems quickly, reliably and accurately are called competent GAs. When the fitness landscape of a problem changes overtime, the problem is called non–stationary, dynamic or time–variant problem. This paper investigates the use of competent GAs for optimizing non–stationary optimization problems. More specifically, we use an information theoretic approach based on the minimum description length principle to adaptively identify regularities and substructures that can be exploited to respond quickly to changes in the environment. We also develop a special type of problems with bounded difficulties to test non–stationary optimization problems. The results provide new insights into non-stationary optimization problems and show that a search algorithm which automatically identifies and exploits possible decompositions is more robust and responds quickly to changes than a simple genetic algorithm. 1

Ensuring building-block (BB) mixing is critical to the success of genetic and evolutionary algorithms. There has been a growing interest in analyzing and understanding BB mixing and it is necessary to organize and categorize representative literature. This paper presents an exhaustive survey of studies on one or more aspects of mixing. In doing so, a classification of the literature based on the role of recombination operators assumed by those studies is developed. Such a classification not only highlights the significant results and unifies existing work, but also provides a foundation for future research in understanding mixing in genetic algorithms.

Abstract not found

Abstract- The paper analyzes the scalability of multiobjective estimation of distribution algorithms (MOEDAs), particularly multiobjective extended compact genetic algorithm (meCGA), on a class of boundedly-difficult additively-separable multiobjective optimization problems. The paper demonstrates that even if the linkage is correctly identified, massive multimodality of the search problems can easily overwhelm the nicher and lead to exponential scale-up. The exponential growth of the Pareto-optimal solutions introduces a fundamental limit on the scalability of MOEDAs and the number of competing sub-structures between the multiple objectives. Facetwise models are subsequently used to predict this limit in the growth rate of the number of differing substructures between the two objectives to avoid the niching method from being overwhelmed and lead to polynomial scalability of MOEDAs. 1

This study investigates the decision making between fitness function with differing variance and computational-cost values. The objective of this decision making is to provide evaluation relaxation and thus enhance the eciency of the genetic search. A decision-making strategy has been developed to maximize speed-up using facetwise models for the convergence time and population sizing. Results indicate that using this decision making, significant speed-up can be obtained.

Ensuring building-block (BB) mixing is critical to the success of genetic and evolutionary algorithms. This study develops facetwise models to predict the BB mixing time and the population sizing dictated by BB mixing for single-point crossover. Empirical results are used to validate these models. The population-sizing model suggests that for moderate-to-large problems, BB mixing---instead of BB decision making and BB supply---bounds the population size required to obtain a solution of constant quality. Furthermore, the population sizing for singlepoint crossover scales as O , where k is the BB size and m is the number of BBs.

This paper proposes an online population size adjustment scheme for genetic algorithms. It utilizes linkage-model-building techniques to calculate the parameters used in facetwise population-sizing models. The methodology is demonstrated using the dependency structure matrix genetic algorithm on a set of boundedly-difficult problems. Empirical results indicate that the proposed method is both efficient and robust. If the initial population size is too large, the proposed method automatically decreases the population size, and thereby yields significant savings in the number of function evaluations required to obtain high-quality solutions; if the initial population size is too small, the proposed scheme increases the population size on-the-fly and thereby avoiding premature convergence. 1

An Anticipatory Classifier System (ACS) is a learning mechanism based on learning classifier systems and the cognitive model of "Anticipatory Behavioral Control". By comparing perceived consequences with its own expectations (anticipations), an ACS is able to learn in multi-step environments. To date, the ACS has proven its abilities in various problems of that kind. It is able to learn latently (i.e. to learn without getting any reward) and it is able to distinguish between non-Markov states. Additionally, an ACS is capable of incrementally building a cognitive map that can be used to do action-planning. Although the ACS has proven to scale up in suitable environments, it depends on certain environmental properties. It believes itself to be the only agent that can change the perceptions received from an environment. Any environmental change is considered and believed to be caused by the executed actions. The ACS learns from the changes by using fixed mechanisms. This paper reveals the properties of an environment that the current ACS assumes to be given. By investigating the problems of the current ACS when violating these properties we believe that this investigation will immediately serve for a better understanding of the ACS and lead to many ideas to improve the current ACS. We will propose some ideas and discuss the important ones in more detail.