Skip to main content

1995 | OriginalPaper | Buchkapitel

From Prime Implicants to Modular Feedforward Networks

verfasst von : Uwe Hartmann

Erschienen in: Artificial Neural Nets and Genetic Algorithms

Verlag: Springer Vienna

Aktivieren Sie unsere intelligente Suche um passende Fachinhalte oder Patente zu finden.

search-config
loading …

The paper utilises prime implicants and minimal polynomials in order to reduce the size of the training set of a neural feedforward network. We propose a heuristic in order to compute reduced polynomials which are often able to reduce the training set since the computation of minimal polynomials is intractable. Further abstractions lead to modular feedforward sub-architectures of neural networks for special training patterns. Finally, we introduce overlapping modular sub-architectures for distinct training patterns.

Metadaten
Titel
From Prime Implicants to Modular Feedforward Networks
verfasst von
Uwe Hartmann
Copyright-Jahr
1995
Verlag
Springer Vienna
DOI
https://doi.org/10.1007/978-3-7091-7535-4_46

Neuer Inhalt