Journal of Mathematical Biology

, Volume 27, Issue 3, pp 327–340

Compensation type algorithms for neural nets: stability and convergence

  • L. J. Cromme
  • I. E. Dammasch

DOI: 10.1007/BF00275816

Cite this article as:
Cromme, L.J. & Dammasch, I.E. J. Math. Biology (1989) 27: 327. doi:10.1007/BF00275816


Plasticity of synaptic connections plays an important role in the temporal development of neural networks which are the basis of memory and behavior. The conditions for successful functional performance of these nerve nets have to be either guaranteed genetically or developed during ontogenesis. In the latter case, a general law of this development may be the successive compensation of disturbances. A compensation type algorithm is analyzed here that changes the connectivity of a given network such that deviations from each neuron's equilibrium state are reduced. The existence of compensated networks is proven, the convergence and stability of simulations are investigated, and implications for cognitive systems are discussed.

Key words

Neural modeling McCulloch-Pitts networks Compensation algorithm Cognitive systems Fixed points (approximate) 

Copyright information

© Springer-Verlag 1989

Authors and Affiliations

  • L. J. Cromme
    • 1
  • I. E. Dammasch
    • 2
  1. 1.Institut für Angewandte Mathematik der Universität GöttingenGöttingenFederal Republic of Germany
  2. 2.Zentrum Anatomie der Universität GöttingenGöttingenFederal Republic of Germany

Personalised recommendations