1989 | OriginalPaper | Buchkapitel
Detection of Minimal Microfeatures by Internal Feedback
verfasst von : J. Kindermann, A. Linden
Erschienen in: 5. Österreichische Artificial-Intelligence-Tagung
Verlag: Springer Berlin Heidelberg
Enthalten in: Professional Book Archive
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
We define the notion of minimal microfeatures and introduce a new method of internal feedback for multilayer networks. Error signals are used to modify the input of a net. When combined with input decay, internal feedback allows the detection of sets of minimal microfeatures, i. e. those subpatterns which the network actually uses for discrimination. Additional noise on the training data increases the number of minimal microfeatures for a given pattern. The detection of minimal microfeatures is a first step towards a subsymbolic system with the capability of self-explanation. The paper provides examples from the domain of letter recognition.