Abstract
This chapter discusses the CINN’s behaviour when driven by a constant input vector. In this situation, precise theorems can be proven about the stability and steady states of the system. These theorems provide a parametric characterization of the CINN’s steady states. The characterization allows us to predict the network’s STM and LTM states given the input vector. We can fashion these results into an algorithm which we call the CINN Algorithm. This algorithm represents a fast and accurate way of emulating the CINN on sequential and fine-grained parallel machines. Its development paves the way for the analyses and simulation experiments of chapters 4 and 5.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1991 Springer Science+Business Media New York
About this chapter
Cite this chapter
Lemmon, M. (1991). The CINN Algorithm. In: Competitively Inhibited Neural Networks for Adaptive Parameter Estimation. The Springer International Series in Engineering and Computer Science, vol 111. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-4044-1_3
Download citation
DOI: https://doi.org/10.1007/978-1-4615-4044-1_3
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-6809-0
Online ISBN: 978-1-4615-4044-1
eBook Packages: Springer Book Archive