Genetic algorithms (GAs) are biologically motivated adaptive systems which have been used, with varying degrees of success, for function optimization. In this study, an abstraction of the basic genetic algorithm, the Equilibrium Genetic Algorithm (EGA), and the GA in turn, are reconsidered within the framework of competitive learning. This new perspective reveals a number of different possibilities for performance improvements. This paper explores population-based incremental learning (PBIL), a method of combining the mechanisms of a generational genetic algorithm with simple competitive learning. The combination of these two methods reveals a tool which is far simpler than a GA, and which out-performs a GA on large set of optimization problems in terms of both speed and accuracy. This paper presents an empirical analysis of where the proposed technique will outperform genetic algorithms, and describes a class of problems in which a genetic algorithm may be able to perform better. Extensions to this algorithm are discussed and analyzed. PBIL and extensions are compared with a standard GA on twelve problems, including standard numerical optimization functions, traditional GA test suite problems, and NP-Complete problems.

Behavior-oriented AI is a scientific discipline that studies how behavior of agents emerges and becomes intelligent and adaptive. Success of the field is defined in terms of success in building physical agents that are capable of maximising their own self-preservation in interaction with a dynamically changing environment. The paper addresses this artificial life route towards artificial intelligence and reviews some of the results obtained so far. 1 Official reference: Steels, L. (1994) The artificial life roots of artificial intelligence. Artificial Life Journal, Vol 1,1. MIT Press, Cambridge. 1 Introduction For several decades, the field of Artificial Intelligence has been pursuing the study of intelligent behavior using the methodology of the artificial [104]. But the focus of this field, and hence the successes, have mostly been on higher order cognitive activities such as expert problem solving. The inspiration for AI theories has mostly come from logic and the cognitive...

Genetic algorithms (GAs) are biologically motivated adaptive systems which have been used, with varying degrees of success, for function optimization. In this study, an abstraction of the basic genetic algorithm, the Equilibrium Genetic Algorithm (EGA), and the GA in turn, are reconsidered within the framework of competitive learning. This new perspective reveals a number of different possibilities for performance improvements. This paper explores population -based incremental learning (PBIL), a method of combining the mechanisms of a generational genetic algorithm with simple competitive learning. The combination of these two methods reveals a tool which is far simpler than a GA, and which out-performs a GA on large set of optimization problems in terms of both speed and accuracy. This paper presents an empirical analysis of where the proposed technique will outperform genetic algorithms, and describes a class of problems in which a genetic algorithm may be able to perform b...

The application of genetic algorithms (GA) to constrained optimization problems has been hindered by the inefficiencies of reproduction and mutation when feasibility of generated solutions is impossible to guarantee and feasible solutions are very difficult to find. Although several authors have suggested the use of both static and dynamic penalty functions for genetic search, this paper presents a general adaptive penalty technique which makes use of feedback obtained during the search along with a dynamic distance metric. The effectiveness of this method is illustrated on two diverse combinatorial applications; (1) the unequalarea, shape-constrained facility layout problem and (2) the series-parallel redundancy allocation problem to maximize system reliability given cost and weight constraints. The adaptive penalty function is shown to be robust with regard to random number seed, parameter settings, number and degree of constraints, and problem instance. 1. Introduction ...

This paper describes a stochastic hill climbing algorithm named SHCLVND to optimize arbitrary vectorial ! ! ! functions. It needs less parameters. It uses normal (Gaussian) distributions to represent probabilities which are used for generating more and more better argument vectors. The -parameters of the normal distributions are changed by a kind of Hebbian learning.

Different mutation operators have been proposed in evolutionary programming, but for each operator there are some types of optimization problems that cannot be solved efficiently. A mixed strategy, integrating several mutation operators into a single algorithm, can overcome this problem. Inspired by evolutionary game theory, this paper presents a mixed strategy evolutionary programming algorithm that employs the Gaussian, Cauchy, Lévy, and single-point mutation operators. The novel algorithm is tested on a set of 22 benchmark problems. The results show that the mixed strategy performs equally well or better than the best of the four pure strategies does, for all of the benchmark problems. Index Terms Design of algorithms; randomized algorithms; global optimization; evolutionary programming; mixed strategy. I.

Abstract--A concept of a bi-population scheme for real-coded GAs consisting of an explorer sub-GA and an exploiter sub-GA is proposed. The explorer sub-GA mainly does exploration so as to avoid being trapped in local optima by means of restart mechanism; and the exploiter sub-GA does exploitation by which search can be performed more precisely in the neighborhood of the best solution obtained so far. An adaptive load balancing between the explorer sub-GA and the exploiter sub-GA is performed by a monitor based on the number of restarts already occurred. The proposed technique showed superior performance for complex multimodal function optimization problems. Key words: Bi-population, explorer sub-GA, exploiter sub-GA, adaptive load balancing 1.

Elevation map generation is an essential component of any autonomous underwater vehicle designed to navigate close to the seafloor because elevation maps are used for obstacle avoidance, path planning and self localization. We present an algorithm for the reconstruction of elevation maps of the seafloor from side-scan sonar backscatter images and sparse bathymetric points coregistered within the image. Given the trajectory for the underwater vehicle, the reconstruction is corrected for the attitude of the side-scan sonar during the image generation process. To perform reconstruction, an arbitrary but computable scattering model is assumed for the seafloor backscatter. The algorithm uses the sparse bathymetric data to generate an initial estimate for the elevation map which is then iteratively refined to fit the backscatter image by minimizing a global error functional. Concurrently, the parameters of the scattering model are determined on a coarse grid in the image by fitting the assum...

65. Mention of trade names or commercial products does not constitute endorsement or recommendation for use. All research projects making conclusions or recommendations based on environmentally related measurements and funded by the Environmental Protection Agency are required to participate in the Agency

Abstract: Genetic Algorithms are widely regarded as being relatively immune to the problems of local minima that affect many optimization schemes. However there are situations in which the population becomes too uniform in composition and the algorithm gets stuck. We discuss the use of a simulated disease mechanism to overcome this problem. The mechanism acts by reducing the fitness of individuals that are similar to the rest of the population, thereby giving a competitive advantage to those individuals that display unusual traits. This disease concept is tested using a simple genetic algorithm example.