Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence

The choice of how to represent the search space for a genetic algorithm (GA) is critical to the GA's performance. Representations are usually engineered by hand and fixed for the duration of the GA run. Here a new method is described in which the degrees of freedom of the representation-i.e. the genes-are increased incrementally. The phenotypic effects of the new genes are randomly drawn from a sp... View full abstract»

Combinatorial optimization problems require computing efforts which grow at least exponentially with the problem dimension. Therefore, the use of the remarkable power of massively parallel systems constitutes an opportunity to be considered for solving significant applications in reasonable times. In this paper, starting from Tabu Search, a general optimization methodology, a parallel version, ori... View full abstract»

In this paper, we present a regionally guided approach to function optimization. The proposed technique is called “Guided Evolutionary Simulated Annealing”. It combines the simulated annealing and simulated evolution in a novel way. The technique has a mechanism that the search will focus on more “promising” areas. The solution is evolved under regional guidance. The charac... View full abstract»

The paper offers sufficient conditions to prove global convergence of non-elitist evolutionary algorithms. If these conditions can be applied they yield bounds of the convergence rate as a by-product. This is demonstrated by an example that can be calculated exactly View full abstract»

Two methods of hybridizing genetic algorithms (GA) with hill-climbing for global optimization are investigated. The first one involves two interwoven levels of optimization-evolution (GA) and individual learning (hill-climbing)-which cooperate in the global optimization process. The second one consists of modifying a GA by the introduction of new genetic operators or by the alteration of tradition... View full abstract»

In this paper, we argue that the general learning abilities of genetic based techniques for concept learning can be improved in order to deal with numeric and symbolic values, tree-structured values, unknown values and user preference biases. The proposed algorithm, called SIA, uses the covering principle of AQ but with a genetic search that may be called several times. The genetic operators use a... View full abstract»

This paper describes the use of genetic algorithm (GA) and simulated annealing (SA) for optimizing the parameters of PID controllers for a 6-DOF robot arm. A GA and a SA are designed to optimal-tune the parameters of the PID controller of each joint for a single step response and for the tracking of other specified trajectories. The GA and the SA are required to optimize evaluation functions relat... View full abstract»

Adding a sharing method to a genetic algorithm promotes the formation and maintenance of stable subpopulations. The paper explores the limits of sharing by deriving closed-form expressions for the expected time to disappearance of a subpopulation. The time to disappearance is shown to be an exponential function of population size, with relative subpopulation fitnesses determining the base of the e... View full abstract»

We concentrate on non-preemptive hard real-time scheduling algorithms. We compare FIFO, EDLF, SRTF and genetic algorithms for solving this problem. The objective of the scheduling algorithm is to dynamically schedule as many tasks as possible such that each task meets its execution deadline, while minimizing the total delay time of all of the tasks. We present a MicroGA that uses a small populatio... View full abstract»

This study theoretically concerns the exploitation of the possibility of acquiring the most suitable strategies for the each agent in multi-agent systems under a dynamically changing environment. A soccer game is employed as an example. The expected and acquired suitable strategies could be respected as the coordinated motions within agents and then evolve by themselves through the experiences of ... View full abstract»

There are two types of GAs with difference of their representation of strings. They are the binary coded GA and the order-based GA. We've already proposed a new type of binary coded GA, called the forking GA (fGA), as a kind of multi-population GA and showed that the searching power of the fGA is superior to the standard GA. The distinguished feature of the fGA is that each population takes a diff... View full abstract»

There have been proposed various approaches for solving the collision avoidance problem of a robot manipulator. However, unfortunately, almost all of the research in this area has so far only dealt with the collision avoidance problem in which moving obstacles are not included in the workspace of a robot manipulator. In this paper, it is shown that path planning and the collision avoidance plannin... View full abstract»

Most of the algorithms for global optimization making use of the concept of population exploit very little of the information provided by agents in the population in order to choose the next point to evaluate. We develop a new method called S.T.E.P. (Select The Easiest Point) which determines the next point to evaluate by analysing the usefulness of evaluating the function at a certain position. M... View full abstract»

The size of the population can be critical in many applications of genetic algorithms. If the population size is too small, the genetic algorithm may converge too quickly; if it is too large, the genetic algorithm may waste computational resources; the waiting time for an improvement might be too long. We propose an adaptive method for maintaining variable population size, which grows and shrinks ... View full abstract»

Optimization of a group of traffic signals over an area is a large, multi-agent-type real-time planning problem without a precise reference model being given. To do this planning, each signal should learn not only to acquire its control plans individually through reinforcement learning, but also to cooperate with other signals. These two objectives-distributed learning of agents and cooperation am... View full abstract»

Production genetic algorithms is proposed to enable grammar structure as well as hardware description language (HDL) programs to evolve, toward an automated hardware design system through an evolutionary process. Evolutionary computation and methods make it possible to design hardware that works in unknown and non-stationary environments without explicit design knowledge. In the proposed system, h... View full abstract»

A new genetic algorithm (GA) for the traveling salesman problem (TSP) is given. Two novel features of this algorithm are: (i) a new locus-based encoding/crossover pair, and (ii) a static preprocessing step which changes the encoding order of the vertices. It is believed that this algorithm is also applicable to other ordering problems, not just TSP. Experimental results on the standard benchmarks ... View full abstract»

The paper presents an approach to dynamic mapping and load balancing of parallel programs in MIMD multicomputers, based on coordinated migration of processes of a parallel program. A program graph is interpreted as a multi-agent system with locally defined goals and actions, operating in some environment. A parallel genetic algorithm (island model) is developed to work out a set of collective deci... View full abstract»

The paper reports on a project which aims to build (i.e. grow/evolve) an artificial brain by the year 2001. This artificial brain should initially contain thousands of interconnected artificial neural network modules, and be capable of controlling approximately 1000 “behaviors” in a “robot kitten”. The name given to this research project is “CAM-Brain”, because ... View full abstract»

The crossover operation is characteristic of genetic algorithms (GAs). This paper analyzes the crossover effect in GAs. We start with two bits, that is the minimum chromosome length to crossover. We compare one operator GAs, using only selection, and two operators GAs by selection and crossover with respect to the expected quality and speed of the convergence. First, we analyse the case of two ind... View full abstract»

This paper describes the application of evolutionary learning and classification tree techniques to the insurance underwriting domain. These machine learning techniques are used to build a knowledge base of rules for an expert system which determines when an insurance policy should be terminated. The effectiveness of each method is compared with the other and a hybrid method is proposed, which com... View full abstract»

In this paper an approach to evolutionary learning based upon principles of cultural evolution is developed. In this dual-inheritance system, there is an evolving population of trait sequences as well as an associated belief space. The belief space is derived from the behavior of individuals and is used to actively constrain the traits acquired in future populations. Shifts in the representation o... View full abstract»

The precise docking of a truck at a loading dock has been proposed in (Nguyen and Widrow, 1990) as a benchmark problem for non-linear control by neural-nets. The main difficulty is that backpropagation is not a priori suitable as a learning paradigm, because no set of training vectors is available: It is non-trivial to find solution trajectories that dock the truck from anywhere in the loading yar... View full abstract»

Rule-based systems used for optical character recognition (OCR) are notoriously difficult to write, maintain, and upgrade. The paper describes a method for using genetic programming (GP) to evolve and upgrade rules for an OCR system. The language of the evolved programs was designed such that human hand-coded rules can be included into the initial population in order to upgrade for a new font. The... View full abstract»