uu.seUppsala universitets publikationer
Ändra sökning
Avgränsa sökresultatet
1 - 3 av 3
RefereraExporteraLänk till träfflistan
Permanent länk
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
Träffar per sida
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sortering
  • Standard (Relevans)
  • Författare A-Ö
  • Författare Ö-A
  • Titel A-Ö
  • Titel Ö-A
  • Publikationstyp A-Ö
  • Publikationstyp Ö-A
  • Äldst först
  • Nyast först
  • Skapad (Äldst först)
  • Skapad (Nyast först)
  • Senast uppdaterad (Äldst först)
  • Senast uppdaterad (Nyast först)
  • Standard (Relevans)
  • Författare A-Ö
  • Författare Ö-A
  • Titel A-Ö
  • Titel Ö-A
  • Publikationstyp A-Ö
  • Publikationstyp Ö-A
  • Äldst först
  • Nyast först
  • Skapad (Äldst först)
  • Skapad (Nyast först)
  • Senast uppdaterad (Äldst först)
  • Senast uppdaterad (Nyast först)
Markera
Maxantalet träffar du kan exportera från sökgränssnittet är 250. Vid större uttag använd dig av utsökningar.
  • 1.
    Fridenfalk, Mikael
    Uppsala universitet, Humanistisk-samhällsvetenskapliga vetenskapsområdet, Historisk-filosofiska fakulteten, Institutionen för speldesign.
    Analytic Method for Evaluation of the Weights of a Robust Large-Scale Multilayer Neural Network2015Ingår i: International Journal On Advances in Networks and Services, ISSN 1942-2644, E-ISSN 1942-2644, Vol. 8, nr 3-4, 139-148 s.Artikel i tidskrift (Refereegranskat)
    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.

  • 2.
    Fridenfalk, Mikael
    Uppsala universitet, Humanistisk-samhällsvetenskapliga vetenskapsområdet, Historisk-filosofiska fakulteten, Institutionen för speldesign.
    Method for Analytic Evaluation of the Weights of a Robust Large-Scale Multilayer Neural Network with Many Hidden Nodes2014Ingår i: ICSEA 2014, The Ninth International Conference on Software Engineering Advances, 2014, 374-378 s.Konferensbidrag (Refereegranskat)
    Abstract [en]

    The multilayer feedforward neural network is presently one of the most popular computational methods in computer science. The current method for the evaluation of its weights is however performed by a relatively slow iterative method known as backpropagation. According to previous research, attempts to evaluate the weights analytically by the linear least square method, showed to accelerate the evaluation process significantly. The evaluated networks showed however to fail in robustness tests 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 a large-scale neural network with many hidden nodes, as an upgrade to the previously suggested analytic method.

  • 3.
    Fridenfalk, Mikael
    Uppsala universitet, Humanistisk-samhällsvetenskapliga vetenskapsområdet, Historisk-filosofiska fakulteten, Institutionen för speldesign.
    The Development and Analysis of Analytic Method as Alternative for Backpropagation in Large-Scale Multilayer Neural Networks2014Ingår i: ADVCOMP 2014, The Eighth International Conference on Advanced Engineering Computing and Applications in Sciences, 2014, 46-49 s.Konferensbidrag (Refereegranskat)
    Abstract [en]

    This paper presents a least-square based analytic solution of the weights of a multilayer feedforward neural network with a single hidden layer and a sigmoid activation function, which today constitutes the most common type of artificial neural networks. This solution has the potential to be effective for large-scale neural networks with many hidden nodes, where backpropagation is known to be relatively slow. At this stage, more research is required to improve the generalization abilities of the proposed method.

1 - 3 av 3
RefereraExporteraLänk till träfflistan
Permanent länk
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