Abstract
In the previous chapter, various topological representations in terms of the kernel memory concept have been discussed together with some illustrative examples. In this chapter, a novel unsupervised algorithm to train the link weights between the KFs is given by extending the original Hebb’s neuropsychological concept, whereby the self-organising kernel memory (SOKM)1 is proposed.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Rights and permissions
About this chapter
Cite this chapter
Hoya, T. The Self-Organising Kernel Memory (SOKM). In: Artificial Mind System - Kernel Memory Approach. Studies in Computational Intelligence, vol 1. Springer, Berlin, Heidelberg. https://doi.org/10.1007/10997444_4
Download citation
DOI: https://doi.org/10.1007/10997444_4
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-26072-1
Online ISBN: 978-3-540-32403-4
eBook Packages: EngineeringEngineering (R0)