Abstract
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.
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.
References
Allen, R.B. Sequential connectionist networks for answering simple questions about a microworld. In Proceedings of the Cognitive Science Society, Montreal, 1988.
J.A. Hendler. Marker-passing over microfeatures: a cautious step towards the subsymbolic. Cognitive Science, 1988.
J. Kindermann and A. Linden. Pattern completion and classification with back-propagation. In J. Kindermann and C. Lischka, editors, Workshop Konnektionismus (Arbeitspapiere der GMD), GMD, 1988.
A. Linden. Lernverfahren fuer neuronale Netze. 1989. Diplomarbeit, in preparation.
A. Linden and J. Kindermann. Constraint satisfaction and pattern completion with enhanced back propagation. In Proceedings of the International Conference Connectionism in Perspective, University of Zurich, 10.-13. October, 1988. to be published.
J.L. McClelland and A.H. Kawamoto. Mechanisms of sentence processing: assigning roles to constituents. In D. E. Rumelhart and J. L. McClelland, editors, Parallel Distributed Processing. Vol I + II, MIT Press, 1986.
R. Miikkulainen and M.G. Dyer. Forming global representations with extended backpropagation. In Proceedings ICNN-88, San Diego, 1988.
D.E. Rumelhart, G.E. Hinton, and R.J. Williams. Learning internal representations by error propagation. In D. E. Rumelhart and J. L. McClelland, editors, Parallel Distributed Processing. Vol. I +II, MIT Press, 1986.
D.E. Rumelhart and J.L. McClelland. On learning the past tenses of english verbs. In D. E. Rumelhart and J. L. McClelland, editors, Parallel Distributed Processing. Vol. I + II, MIT Press, 1986.
W.S. Stornetta and B.A. Huberman. An improved three-layer backpropagation algorithm. In Proceedings ICNN-87, San Diego, 1987.
P.J. Werbos. Beyond reasoning: new tools for prediction and analysis in the behavioral sciences. 1974. PhD thesis, Harvard University.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1989 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kindermann, J., Linden, A. (1989). Detection of Minimal Microfeatures by Internal Feedback. In: Retti, J., Leidlmair, K. (eds) 5. Österreichische Artificial-Intelligence-Tagung. Informatik-Fachberichte, vol 208. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-74688-8_28
Download citation
DOI: https://doi.org/10.1007/978-3-642-74688-8_28
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-51039-0
Online ISBN: 978-3-642-74688-8
eBook Packages: Springer Book Archive