uu.seUppsala universitets publikationer
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Analytic Method for Evaluation of the Weights of a Robust Large-Scale Multilayer Neural Network
Uppsala universitet, Humanistisk-samhällsvetenskapliga vetenskapsområdet, Historisk-filosofiska fakulteten, Institutionen för speldesign.ORCID-id: 0000-0002-3754-172X
2015 (Engelska)Ingår i: International Journal On Advances in Networks and Services, ISSN 1942-2644, E-ISSN 1942-2644, Vol. 8, nr 3-4, s. 139-148Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

The multilayer feedforward neural network is presently one of the most popular computational methods in computer science. However, the current method for the evaluation of its weights is performed by a relatively slow iterative method known as backpropagation. According to previous research on a large-scale neural network with many hidden nodes, attempts to use an analytic method for the evaluation of the weights by the linear least square method showed to accelerate the evaluation process significantly. Nevertheless, the evaluated network showed in preliminary tests to fail in robustness compared to well-trained networks by backpropagation, thus resembling overtrained networks. This paper presents the design and verification of a new method that solves the robustness issues for such a neural network, along with MATLAB code for the verification of key experiments.

Ort, förlag, år, upplaga, sidor
2015. Vol. 8, nr 3-4, s. 139-148
Nyckelord [en]
Analytic, big data, FNN, large-scale, least square method, multilayer, neural network, robust, sigmoid.
Nationell ämneskategori
Datorsystem
Forskningsämne
Datavetenskap; Matematik med inriktning mot tillämpad matematik
Identifikatorer
URN: urn:nbn:se:uu:diva-270128OAI: oai:DiVA.org:uu-270128DiVA, id: diva2:890185
Anmärkning

In press

Tillgänglig från: 2015-12-31 Skapad: 2015-12-21 Senast uppdaterad: 2017-12-01Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Fulltext

Personposter BETA

Fridenfalk, Mikael

Sök vidare i DiVA

Av författaren/redaktören
Fridenfalk, Mikael
Av organisationen
Institutionen för speldesign
I samma tidskrift
International Journal On Advances in Networks and Services
Datorsystem

Sök vidare utanför DiVA

GoogleGoogle Scholar

urn-nbn

Altmetricpoäng

urn-nbn
Totalt: 991 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf