Novel back propagation optimization by Cuckoo Search algorithm.

The traditional Back Propagation (BP) has some significant disadvantages, such as training too slowly, easiness to fall into local minima, and sensitivity of the initial weights and bias. In order to overcome these shortcomings, an improved BP network that is optimized by Cuckoo Search (CS), called...

Descripción completa

Detalles Bibliográficos
Publicado en:Scientific World Journal pp. 878262 - 878263
Autores principales: Yi, Jiao-Hong, Xu, Wei-Hong, Chen, Yuan-Tao
Formato: research Journal Article
Publicado: Wiley-Blackwell 2014
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=103834300&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 103834300
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        1537744X
        1BX5
      jtl: Scientific World Journal
      issn: 1537744X
      maglogo: N
    pubinfo:
      dt: 2014
      pid: 480
      pub: Wiley-Blackwell
      place: Malden, Massachusetts
    artinfo:
      ui:
        103834300
        103834300
        NLM25028682
        2012650695
        10.1155/2014/878262
        NLM25028682
        PMC3980988
        103834300
      ppf: 878262
      ppct: 1
      formats:
      tig:
        atl: Novel back propagation optimization by Cuckoo Search algorithm.
      aug:
        au:
          Yi, Jiao-Hong
          Xu, Wei-Hong
          Chen, Yuan-Tao
        affil: School of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha, Hunan 410014, China.
      sug:
        subj:
          Algorithms
          Models, Theoretical
          Neural Networks (Computer)
      ab: The traditional Back Propagation (BP) has some significant disadvantages, such as training too slowly, easiness to fall into local minima, and sensitivity of the initial weights and bias. In order to overcome these shortcomings, an improved BP network that is optimized by Cuckoo Search (CS), called CSBP, is proposed in this paper. In CSBP, CS is used to simultaneously optimize the initial weights and bias of BP network. Wine data is adopted to study the prediction performance of CSBP, and the proposed method is compared with the basic BP and the General Regression Neural Network (GRNN). Moreover, the parameter study of CSBP is conducted in order to make the CSBP implement in the best way.
      pubtype: Academic Journal
      doctype:
        research
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N