International Conference on Artificial Neural Networks

ICANN 2005: Artificial Neural Networks: Formal Models and Their Applications – ICANN 2005 pp 295-300

Induced Weights Artificial Neural Network

  • Slawomir Golak
Conference paper

DOI: 10.1007/11550907_47

Volume 3697 of the book series Lecture Notes in Computer Science (LNCS)
Cite this paper as:
Golak S. (2005) Induced Weights Artificial Neural Network. In: Duch W., Kacprzyk J., Oja E., Zadrożny S. (eds) Artificial Neural Networks: Formal Models and Their Applications – ICANN 2005. ICANN 2005. Lecture Notes in Computer Science, vol 3697. Springer, Berlin, Heidelberg

Abstract

It is widely believed in the pattern recognition field that the number of examples needed to achieve an acceptable level of generalization ability depends on the number of independent parameters needed to specify the network configuration. The paper presents a neural network for classification of high-dimensional patterns. The network architecture proposed here uses a layer which extracts the global features of patterns. The layer contains neurons whose weights are induced by a neural subnetwork. The method reduces the number of independent parameters describing the layer to the parameters describing the inducing subnetwork.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Slawomir Golak
    • 1
  1. 1.Electrotechnology Department, Division of Informatics and Modeling of Technological ProcessesSielsian University of TechnologyPoland