Showing papers on "Particle swarm optimization published in 1997"

A discrete binary version of the particle swarm algorithm

Abstract: The particle swarm algorithm adjusts the trajectories of a population of "particles" through a problem space on the basis of information about each particle's previous best performance and the best previous performance of its neighbors. Previous versions of the particle swarm have operated in continuous space, where trajectories are defined as changes in position on some number of dimensions. The paper reports a reworking of the algorithm to operate on discrete binary variables. In the binary version, trajectories are changes in the probability that a coordinate will take on a zero or one value. Examples, applications, and issues are discussed.

The particle swarm: social adaptation of knowledge

Abstract: Particle swarm adaptation is an optimization paradigm that simulates the ability of human societies to process knowledge The algorithm models the exploration of a problem space by a population of individuals; individuals' successes influence their searches and those of their peers The algorithm is relevant to cognition, in particular the representation of schematic knowledge in neural networks Particle swarm optimization successfully optimizes network weights, simulating the adaptive sharing of representations among social collaborators The paper introduces the algorithm, begins to develop a social science context for it, and explores some aspects of its functioning

Using the particle swarm optimization technique to train a recurrent neural model

Abstract: We discuss the results of implementing an evolutionary learning technique entitled particle swarm optimization as described by Kennedy and Eberhart (1995). We present a number of results using this technique on a number of neural model architectures using the XOR problem and then conclude by applying it to a real problem-parsing natural language phrases.