Parallel Problem Solving from Nature [[electronic resource] ] : 1st Workshop, PPSN I Dortmund, FRG, October 1-3, 1990. Proceedings / / edited by Hans-Paul Schwefel, Reinhard Männer

• Record Nr.: UNISA996465530303316
• Pubbl/distr/stampa: Berlin, Heidelberg : , : Springer Berlin Heidelberg : , : Imprint : Springer, , 1991
• ISBN: 3-540-70652-6
• Edizione: [1st ed. 1991.]
• Descrizione fisica: 1 online resource (XI, 489 p.)
• Collana: Lecture Notes in Computer Science, , 0302-9743 ; ; 496
• Disciplina: 004/.35
• Soggetti: Applied mathematics; Engineering mathematics; Architecture, Computer; Computers; Algorithms; Microprocessors; Applications of Mathematics; Computer System Implementation; Theory of Computation; Computation by Abstract Devices; Algorithm Analysis and Problem Complexity; Processor Architectures
• Lingua di pubblicazione: Inglese
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Note generali: Bibliographic Level Mode of Issuance: Monograph
• Nota di contenuto: Global convergence of genetic algorithms: A markov chain analysis -- The theory of virtual alphabets -- Towards an optimal mutation probability for genetic algorithms -- An alternative Genetic Algorithm -- An analysis of the interacting roles of population size and crossover in genetic algorithms -- Gleam a system for simulated "intuitive learning" -- Genetic algorithms and highly constrained problems: The time-table case -- An evolution standing on the design of redundant manipulators -- Redundant coding of an NP-complete problem allows effective Genetic Algorithm search -- Circuit partitioning with genetic ; algorithms using a coding scheme to preserve the structure of a circuit -- Genetic algorithms, production plan optimisation and scheduling -- System identification using genetic algorithms -- Conformational analysis of DNA using genetic algorithms -- Operator-oriented genetic algorithm and its application to sliding block puzzle problem -- A topology exploiting genetic algorithm to control dynamic systems -- Genetic local search algorithms for the traveling salesman problem -- Genetic programming artificial nervous systems artificial embryos and embryological electronics -- Concept formation and decision tree induction using the genetic programming paradigm -- On solving travelling salesman problems by genetic algorithms -- Genetic algorithms and punctuated equilibria in VLSI -- Implementing the genetic algorithm on transputer based parallel processing systems -- Explicit parallelism of genetic algorithms through population structures -- Parallel genetic packing of rectangles -- Partitioning a graph with a parallel genetic algorithm -- Solving the mapping-problem — Experiences with a genetic algorithm -- Optimization using distributed genetic algorithms -- Application of the Evolutionsstrategie to discrete optimization problems -- A variant of evolution strategies for vector optimization -- Application of evolution strategy in parallel populations -- Global optimization by means of distributed evolution strategies -- Solving sequential games with Boltzmann-learned tactics -- Optimizing simulated annealing -- Parallel Implementations Of Simulated Annealing / A local timing model for parallel optimization with Boltzmann Machines -- Error-free parallel implementation of simulated annealing -- Trimm: A parallel processor for image reconstruction by simulated annealing -- The response-time constraint in neural evolution -- An artificial neural network representation for artificial organisms -- Feature construction for back-propagation -- Improved convergence rate of back-propagation with dynamic adaption of the learning rate -- Performance evaluation of evolutionarily created neural network topologies -- Optical image preprocessing for neural network classifier system -- Gannet: Genetic design of a neural net for face recognition -- The application of a genetic approach as an algorithm for neural networks -- Genetic improvements of feedforward nets for approximating functions -- Exploring adaptive agency III: Simulating the evolution of habituation and sensitization -- A learning strategy for neural networks based on a modified evolutionary strategy -- Genetic algorithms and the immune system -- Selectionist categorization -- A classifier system with integrated genetic operators -- The fuzzy classifier system: Motivations and first results -- Hints for adaptive problem solving gleaned from immune networks -- A reactive robot navigation system based on a fluid dynamics metaphor -- Transfer of natural metaphors to parallel problem solving applications -- Modelling and simulation of distributed evolutionary search processes for function optimization -- Parallel, decentralized spatial mapping for robot navigation and path planning -- Ecological dynamics under different selection rules in distributed and iterated prisoner's dilemma game -- Adaptation in signal spaces -- A principle of minimum complexity in evolution -- The emergence of data structures from local interactions -- The view from the adaptive landscape -- Boltzmann-, Darwin- and Haeckel-strategies in optimization problems -- Optimizing complex problems by nature's algorithms: Simulated annealing and evolution strategy—a comparative study -- Genetic Algorithms and evolution strategies: Similarities and differences -- Building the ultimate machine: The emergence of artificial cognition.
• Sommario/riassunto: With the appearance of massively parallel computers, increased attention has been paid to algorithms which rely upon analogies to ; natural processes. This development defines the scope of the PPSN conference at Dortmund in 1990 whose proceedings are presented in this volume. The subjects treated include: - Darwinian methods such as evolution strategies and genetic algorithms; - Boltzmann methods such as simulated annealing; - Classifier systems and neural networks; - Transfer of natural metaphors to artificial problem solving. The main objectives of the conference were: - To gather theoretical results about and experimental comparisons between these algorithms, - To discuss various implementations on different parallel computer architectures, - To summarize the state of the art in the field, which was previously scattered widely both among disciplines and geographically.