Justification of Neural Modeling

  • Teuvo Kohonen
Part of the Springer Series in Information Sciences book series (SSINF, volume 30)

Abstract

Two different motives are discernible in neural modeling. The original one is an attempt to describe biophysical phenomena that take place in real biological neurons, whereby it may be expected that some primitives or basic elements of information processing by the brain could be isolated and identified. Another one is a direct attempt to develop new devices based on heuristically conceived, although biologically inspired simple components such as threshold-logic units or formal neurons. The circuits thereby designed are usually called artificial neural networks (ANNs).

Keywords

Covariance Agglomeration cosB 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Teuvo Kohonen
    • 1
  1. 1.Neural Networks Research CentreHelsinki University of TechnologyEspooFinland

Personalised recommendations