Abstract
When solving a multi-classification problem with k kinds of samples, if we use a multiple linear perceptron, k output nodes will be widely-used. In this paper, we introduce binary output units of multiple linear perceptron by analyzing the classification problems of vertices of the regular hexahedron in the Three-dimensional Euclidean Space. And we define Binary Approach and One-for-Each Approach to the problem. Then we obtain a theorem with the help of which we can find a Binary Approach that requires more less classification planes than the One-for-Each Approach when solving a One-for-Each Separable Classification Problem. When we apply the Binary Approach to the design of output units of multiple linear perceptron, the output units required will decrease greatly and more problems could be solved.
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
Wu, W., Zhou, C.G., Liang, Y.C.: Intelligent computing. Higher Education Press, Beijing (2009)
Haykin, S.: Neural Networks and Learing Machines, 3rd edn. China Machine Press (2009)
SateeshBabu, G., Suresh, S.: Meta-cognitive Neural Network for classification problems in a sequential learning framework. Neurocomputing 81, 86–96 (2012)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sun, Q., Liu, Y., Li, Z., Yang, S., Wu, W., Jin, J. (2013). The Binary Output Units of Neural Network. In: Guo, C., Hou, ZG., Zeng, Z. (eds) Advances in Neural Networks – ISNN 2013. ISNN 2013. Lecture Notes in Computer Science, vol 7951. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-39065-4_31
Download citation
DOI: https://doi.org/10.1007/978-3-642-39065-4_31
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-39064-7
Online ISBN: 978-3-642-39065-4
eBook Packages: Computer ScienceComputer Science (R0)