Showing papers on "Evolutionary programming published in 1992"
Book•
01 Jan 1992
TL;DR: GAs and Evolution Programs for Various Discrete Problems, a Hierarchy of Evolution Programs and Heuristics, and Conclusions.
Abstract: 1 GAs: What Are They?.- 2 GAs: How Do They Work?.- 3 GAs: Why Do They Work?.- 4 GAs: Selected Topics.- 5 Binary or Float?.- 6 Fine Local Tuning.- 7 Handling Constraints.- 8 Evolution Strategies and Other Methods.- 9 The Transportation Problem.- 10 The Traveling Salesman Problem.- 11 Evolution Programs for Various Discrete Problems.- 12 Machine Learning.- 13 Evolutionary Programming and Genetic Programming.- 14 A Hierarchy of Evolution Programs.- 15 Evolution Programs and Heuristics.- 16 Conclusions.- Appendix A.- Appendix B.- Appendix C.- Appendix D.- References.
12,212 citations
01 Jan 1992
TL;DR: It is argued that all three forms of intelligence are equivalent in process and that all intelligent systems are inherently evolutionary in nature.
Abstract: The majority of research in artificial intelligence has been devoted to modeling the symptoms of intelligent behavior as we observe them in ourselves Investigation into the causative factors of intelligence have been passed over in order to more rapidly obtain the immediate consequences of intelligence The results of these efforts have been computer programs that achieve outstanding performance, but only in very limited domains of application
It is suggested that attention be given to the mechanisms that generate intelligence Intelligence may be defined as that property which enables a system to adapt its behavior to meet desired goals in a range of environments Three organizational forms of intelligence are characterized within the present discussion: (1) phylogenetic (arising within the phyletic line of descent), (2) ontogenetic (arising within the individual), and (3) sociogenetic (arising within the group) It is argued that all three forms of intelligence are equivalent in process and that all intelligent systems are inherently evolutionary in nature
Simulating natural evolution provides a method for machine generated intelligent behavior A series of experiments is conducted to quantify the efficiency and effectiveness of evolutionary problem solving The results indicate that this "evolutionary programming" can rapidly discover nearly optimum solutions to a broad range of problems Mathematical analysis of the algorithm and its variations indicates that the process will converge to the global best available solution Automatic control and gaming experiments are conducted in which an evolutionary program must discover suitable strategies for solving the task at hand No credit assignment or other heuristic evaluations are offered to the evolutionary programs The results indicate the utility of using simulated evolution for general problem solving
265 citations
TL;DR: In this paper, a model of design is described as a series of transformation processes and extended to include the behaviour of the designed product in its environment, which is then recast through an analogy with natural evolution as an evolutionary process model through the inclusion of the evolutionary-style processes of cross-over and mutation and the introduction of design genes.
92 citations
TL;DR: Any successful strategy for a new synthesis requires both a new conceptual insight of evolving systems, and tactical devices for analyzing new specific aspects of the evolutionary process.
Abstract: The goal of evolutionary theory is to (a) specify the general causal structure of evolving systems and (b) analyze evolutionary consequences that are expected to result from the proposed structure of the model systems. Biologists frequently emphasize the hypothetico-deductive method in evolutionary theory. I will show that this method primarily provides a tactical device for (b), while evolutionary synthesis requires a foundation of a unifying conceptual model for (a). Therefore, any successful strategy for a new synthesis requires both a new conceptual insight of evolving systems, and tactical devices for analyzing new specific aspects of the evolutionary process.
11 citations
TL;DR: In this paper, the fundamental properties of natural evolution are simulated for the purpose of modeling a set of ocean acoustic signals, and experimental results indicate that simulated evolution provides a method for estimating both the appropriate order and parameter values of a model.
Abstract: The process of natural evolution is used as a basis for a search technique that can locate the extremum of complex response surfaces despite the existence of multiple local minima or maxima. Background on research in simulated evolution is offered. The fundamental properties of natural evolution are simulated for the purpose of modeling a set of ocean acoustic signals. The experimental results indicate that simulated evolution provides a method for estimating both the appropriate order and parameter values of a model. Some theoretical comparisons are made to standard estimation methods. >
11 citations
01 Nov 1992
TL;DR: In this article, the authors investigated the application of an evolutionary search strategy for determining near-optimal mobile manipulator configurations by incorporating joint torques, obstacle avoidance and manipulability in a multi-criteria optimization formulation.
Abstract: Multi-degree-of-freedom manipulators are becoming commonplace on mobile platforms. Full autonomy of mobile manipulator robotic systems will depend on the ability to resolve the inherent kinematic redundancy in task commutation. This work investigates the application of an evolutionary search strategy for determining near-optimal mobile manipulator configurations. Joint torques, obstacle avoidance and manipulability are incorporated in a multi-criteria optimization formulation. A variety of aspects of the evolutionary programming paradigm are addressed via empirical studies on a two degree-of-freedom (DOF) manipulator. These studies investigate full configuration vector versus partial configuration vector mutation as well as mutation strategies which incorporate cost and iteration number. The results of this study are then applied to a planar three DOF manipulator mounted on a single DOF mobile base. Experiments indicate that the configuration optimization problem is amenable to a variety of mutation strategies.
10 citations
16 Dec 1992
TL;DR: The chosen stochastic search method is capable of simultaneously evolving both network architecture and weights, and the number of synapses and neurons are incorporated into an objective function so that network parameter optimization is done with respect to computational costs and mean pattern error.
Abstract: This work investigates the application of a stochastic search technique, evolutionary programming, for developing self-organizing neural networks. The chosen stochastic search method is capable of simultaneously evolving both network architecture and weights. The number of synapses and neurons are incorporated into an objective function so that network parameter optimization is done with respect to computational costs as well as mean pattern error. Experiments are conducted using feedforward networks for simple binary mapping problems.
10 citations
26 Oct 1992
TL;DR: The application of evolutionary programming, a stochastic search technique, for determining connectivity in feedforward neural networks, is investigated and results are shown using feedforward networks for simple binary mapping problems.
Abstract: The application of evolutionary programming, a stochastic search technique, for determining connectivity in feedforward neural networks, is investigated. The method is capable of simultaneously evolving both the connection scheme and the network weights. The number of synapses is incorporated into an objective function so that network parameter optimization is done with respect to a connectivity cost as well as mean pattern error. Experimental results are shown using feedforward networks for simple binary mapping problems. >
8 citations
Proceedings Article•
01 Jan 1992TL;DR: The development of the evolutionary computer is based on three sources: the concept of adaptive identification in the specified class of structured models, algorithmic facilities and software of data processing developed for the purpose of classification, recognition, prediction, reconstruction, and design.
Abstract: The development of the evolutionary computer is based on three sources: the concept of adaptive identification in the specified class of structured models, algorithmic facilities and software of data processing developed for the purpose of classification, recognition, prediction, reconstruction, and design; and a component base developed for realizing the hardware support of evolutionary algorithms by modern facilities of opto- and microelectronics. The basic concepts pertaining to an evolutionary computer are formulated. It is pointed out that the evolutionary processing of information is, as a whole, a process of adaptive structured identification of the decision rule, which incorporates the evolutionary synthesis of the decision rule and the formation of the actual decision. A special-purpose processor realization of evolutionary processing is discussed. >
7 citations
Proceedings Article•
01 Jan 1992
TL;DR: Simulated evolution can be used as an effective numerical optimization procedure and some mathematical properties of specific evolutionary techniques, such as evolutionary programming and genetic algorithms, are detailed.
Abstract: Simulated evolution can be used as an effective numerical optimization procedure. The robust nature of stochastic search can be applied to general problem solving. Recent research in simulated evolution has been applied to neural network design and training, automatic control, system identification and other combinatorial problems. A brief review of these methods is offered. Some mathematical properties of specific evolutionary techniques, such as evolutionary programming and genetic algorithms, are detailed. Function optimization experiments are conducted to illustrate the mathematical procedures. >