Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top
Neural Computing and Applications
Published in: Neural Computing and Applications 2/2010

01-03-2010 | Original Article

Learning as a nonlinear line of attraction in a recurrent neural network

Authors: Ming-Jung Seow, Vijayan K. Asari, Adam Livingston

Published in: Neural Computing and Applications | Issue 2/2010

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

A method to embed N dimensional, multi-valued patterns into an auto-associative memory represented as a nonlinear line of attraction in a fully connected recurrent neural network is presented in this paper. The curvature of the nonlinear attractor is defined by the Kth degree polynomial line which best fits the training data in N dimensional state space. The width of the nonlinear line is then characterized by the statistical characteristics of the training patterns. Stability of the recurrent network is verified by analyzing the trajectory of the points in the state space during convergence. The performance of the network is benchmarked through the reconstruction of original gray-scale images from their corrupted versions. It is observed that the proposed method can quickly and successfully reconstruct each image with an average convergence rate of 3.10 iterations.
previous article Parsimonious genetic programming for complex process intelligent modeling: algorithm and applications

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now
Literature
1.
Hopfield JJ (1982) Neural networks and physical systems with emergent collective computational abilities. Proc Natl Acad Sci 79(8):2554–2558CrossRefMathSciNet
2.
Zhao L, Caceres JCG, Szu H (2003) Chaotic associative recalls for fixed point attractor patterns. Proc IEEE Int Conf Neural Netw 2:841–845
3.
Seow MJ, Asari VK (2003) Associative memory using ratio rule for multi-valued pattern association. Proc IEEE Int Conf Neural Netw 4:2518–2522
4.
Seow MJ, Asari VK (2006) Ratio rule and homomorphic filter for enhancement of digital color image. J Neurocomput 69:954–958CrossRef
5.
Brody CD, Kepecs RA (2003) Basic mechanisms for graded persistent activity: discrete attractors, continuous attractors, and dynamic representations. Curr Opin Neurobiol 13:204–211CrossRef
6.
Stringer SM, Trappenberg TP, Rolls ET, de Araujo IET (2002) Self-organizing continuous attractor networks and path integration: one-dimensional models of head direction cells. Netw Comput Neural Syst 13:217–242MATH
7.
Seung HS (1998) Continuous attractors and oculomotor control. Neural Netw 11:1253–1258CrossRef
8.
Seow MJ, Asari VK (2004) Recurrent network as a nonlinear line attractor for skin color association. Advances in Neural Networks—ISNN 2004. LNCS vol 3174. Springer, Berlin, pp 870–875
9.
Seow MJ, Asari VK (2005) Color characterization and balancing by a nonlinear line attractor network for image enhancement. Neural Process Lett 22:291–309CrossRef
10.
Seow MJ, Asari VK (2006) Recurrent neural network as a linear attractor for pattern association. IEEE Trans Neural Netw 17:246–250CrossRef
11.
Yi Z, Tan KK (2004) Multistability analysis of discrete recurrent neural networks with unsaturating piecewise linear transfer functions. IEEE Trans Neural Netw 15(2):329–336CrossRef
12.
Cambell WM, Assaleh KT, Broun CC (2002) Speaker recognition with polynomial classifiers. IEEE Trans Speech Audio Proc 10(4):205–212CrossRef
13.
Jankowski S, Lozowski A, Zurada JM (1996) Complex-valued multi-state neural network associative memory. IEEE Trans Neural Netw 7:1491–1496CrossRef
14.
Muezzinoglu MK, Guzelis C, Zurada JM (2003) A new design method for complex-valued multi-state Hopfield associative memory. IEEE Trans Neural Netw 14(4):891–899CrossRef
Metadata
Title
Learning as a nonlinear line of attraction in a recurrent neural network
Authors
Ming-Jung Seow
Vijayan K. Asari
Adam Livingston
Publication date
01-03-2010
Publisher
Springer-Verlag
Published in
Neural Computing and Applications / Issue 2/2010
Print ISSN: 0941-0643
Electronic ISSN: 1433-3058
DOI
https://doi.org/10.1007/s00521-009-0304-9

Other articles of this Issue 2/2010

Neural Computing and Applications 2/2010 Go to the issue

Editorial

Advances in design and application of neural networks

Original Article

Implementation of an LVQ neural network with a variable size: algorithmic specification, architectural exploration and optimized implementation on FPGA devices

Original Article

A hybrid genetic based functional link artificial neural network with a statistical comparison of classifiers over multiple datasets

Original Article

MLP bilinear separation

Original Article

An improved approximation approach incorporating particle swarm optimization and a priori information into neural networks

KES 2008

Application of neural processing paradigm in visual landmark recognition and autonomous robot navigation

Premium Partner

    Image Credits