This paper: 1) reviews different combinations between ANN's and evolutionary algorithms (EA's), including using EA's to evolve ANN connection weights, architectures, learning rules, and input features; 2) discusses different search operators which have been used in various EA's; and 3) points out possible future research directions. It is shown, through a considerably large literature review, that combinations between ANN's and EA's can lead to significantly better intelligent systems than relying on ANN's or EA's alone

Abstract | In this paper we describe the evolution of a discrete-time recurrent neural network to control a real mobile robot. In all our experiments the evolutionary procedure is carried out entirely on the physical robot without human intervention. We showthat the autonomous development of a set of behaviors for locating a battery charger and periodically returning to it can be achieved by lifting constraints in the design of the robot/environment interactions that were employed in a preliminary experiment. The emergent homing behavior is based on the autonomous development ofaninternal neural topographic map (which is not pre-designed) that allows the robot to choose the appropriate trajectory as function of location and remaining energy.

Standard methods for inducing both the structure and weight values of recurrent neural networks fit an assumed class of architectures to every task. This simplification is necessary because the interactions between network structure and function are not well understood. Evolutionary computation, which includes genetic algorithms and evolutionary programming, is a population-based search method that has shown promise in such complex tasks. This paper argues that genetic algorithms are inappropriate for network acquisition and describes an evolutionary program, called GNARL, that simultaneously acquires both the structure and weights for recurrent networks. This algorithm's empirical acquisition method allows for the emergence of complex behaviors and topologies that are potentially excluded by the artificial architectural constraints imposed in standard network induction methods. To Appear in: IEEE Transactions on Neural Networks January The Ohio State University January 17, 1996 1 ...

The paper describes the results of the evolutionary development of a real, neural-network driven mobile robot. The evolutionary approach tothe development of neural controllers for autonomous agents has been successfully used by many researchers, but most-if not all- studies have been carried out with computer simulations. Instead, in this research the whole evolutionary process takes places entirely on a real robot without human intervention. Although the experiments described here tackle a simple task of navigation and obstacle avoidance, we show a number of emergent phenomena that are characteristic of autonomous agents. The neural controllers of the evolved best individuals display a full exploitation of non-linear and recurrent connections that make them more e cient than analogous man-designed agents. In order to fully understand and describe the robot behavior, we have also employed quantitative ethological tools [13], and showed that the adaptation dynamics conform to predictions made for animals. 1

Research on potential interactions between connectionist learning systems, i.e., artificial neural networks (ANNs), and evolutionary search procedures, like genetic algorithms (GAs), has attracted a lot of attention recently. Evolutionary ANNs (EANNs) can be considered as the combination of ANNs and evolutionary search procedures. This paper first distinguishes among three kinds of evolution in EANNs, i.e., the evolution of connection weights, of architectures and of learning rules. Then it reviews each kind of evolution in detail and analyses critical issues related to different evolutions. The review shows that although a lot of work has been done on the evolution of connection weights and of architectures, few attempts have been made to understand the evolution of learning rules. Interactions among different evolutions are seldom mentioned in current research. However, the evolution of learning rules and its interactions with other kinds of evolution play a vital role in EANNs. As t...

The conventional understanding of genetic algorithms depends upon analysis by schemata and the notion of intrinsic parallelism. For this reason, only k-ary string representations have had any formal basis and non-standard representations and operators have been regarded largely as heuristics, rather than principled algorithms. This paper extends the analysis to general representations through identification of schemata as equivalence classes induced by implicit equivalence relations over the space of chromosomes.

Abstract not found

Abstract not found

Abstract not found

This paper presents a theory of convergence for real-coded genetic algorithms---GAs that use floating-point or other high-cardinality codings in their chromosomes. The theory is consistent with the theory of schemata and postulates that selection dominates early GA performance and restricts subsequent search to intervals with above-average function value, dimension by dimension. These intervals may be further subdivided on the basis of their attraction under genetic hillclimbing. Each of these subintervals is called a virtual character, and the collection of characters along a given dimension is called a virtual alphabet. It is the virtual alphabet that is searched during the recombinative phase of the genetic algorithm, and in many problems this is sufficient to ensure that good solutions are found. Although the theory helps suggest why many problems have been solved using real-coded GAs, it also suggests that real-coded GAs can be blocked from further progress in those situations whe...