Time-series forecasting with evolvable partially connected artificial neural network

Mina Moradi Kordmahalleh, Mohammad Gorji Sefidmazgi, Abdollah Homaifar, B. K.C. Dukka, Anthony Guiseppi-Elie

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Scopus citations

Abstract

In nonlinear and chaotic time series prediction, constructing the mathematical model of the system dynamics is not an easy task. Partially connected Artificial Neural Network with Evolvable Topology (PANNET) is a new paradigm for prediction of chaotic time series without access to the dynamics and essential memory depth of the system. Evolvable topology of the PANNET provides flexibility in recognition of systems in contrast to fixed layered topology of the traditional ANNs. This evolvable topology guides the relationship between observation nodes and hidden nodes, where hidden nodes are extra nodes that play the role of memory or internal states of the system. In the proposed variable-length Genetic Algorithm (GA), internal neurons can be connected arbitrarily to any type of nodes. Besides, number of neurons, inputs and outputs for each neuron, origin and weight of each connection evolve in order to find the best configuration of the network.

Original languageEnglish (US)
Title of host publicationGECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference
PublisherAssociation for Computing Machinery
Pages79-80
Number of pages2
ISBN (Print)9781450328814
DOIs
StatePublished - 2014
Event16th Genetic and Evolutionary Computation Conference, GECCO 2014 - Vancouver, BC, Canada
Duration: Jul 12 2014Jul 16 2014

Publication series

NameGECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference

Other

Other16th Genetic and Evolutionary Computation Conference, GECCO 2014
CountryCanada
CityVancouver, BC
Period7/12/147/16/14

Keywords

  • Artificial Neural Networks
  • Evolutionary computation
  • Evolvable Topology
  • Genetic algorithms
  • Time series forecasting

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Applied Mathematics

Fingerprint Dive into the research topics of 'Time-series forecasting with evolvable partially connected artificial neural network'. Together they form a unique fingerprint.

Cite this