Abstract
In this paper, we consider the design of a non-parametric learning machine without a teacher. Most pattern recognition problems may be categorized as parametric or non-parametric on the basis of knowledge that we have concerning the conditional densities of the input patterns. Problems in which the densities are completely unknown are called non-parametric. In addition, the learning machine can be further classified into two types. One is a supervised machine, that is, a machine with an external teacher. In this case, the teacher gives the information regarding the category to which the input pattern belongs and the information regarding the correctness of the machine’s action. The second type is an unsupervised machine.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
C. V. Jakowatz, et al.; “Adaptive Waveform Recognition,” The 4th International Symposium on Information Theory, London, 1960.
N. J. Nilsson, Learning Machines, McGraw-Hill Book Co., 1965.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1971 Plenum Press, New York
About this chapter
Cite this chapter
Shimura, M. (1971). A Mixed-Type Non-Parametric Learning Machine without a Teacher. In: Fu, K.S. (eds) Pattern Recognition and Machine Learning. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-7566-5_4
Download citation
DOI: https://doi.org/10.1007/978-1-4615-7566-5_4
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4615-7568-9
Online ISBN: 978-1-4615-7566-5
eBook Packages: Springer Book Archive