Abstract
In Chap. 13, a series of NN models were described which can be used for supervised learning. In supervised learning the output for an associated input vector is already known and is used to guide the learning process. For example, in training a multilayer perceptron (MLP) the weights on arcs are adjusted in response to the difference which arises at the output node(s) between the MLP’s output and the correct, known, output for a given training vector. The network is therefore trained using a feedback mechanism.
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.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Brabazon, A., O’Neill, M., McGarraghy, S. (2015). Neural Networks for Unsupervised Learning. In: Natural Computing Algorithms. Natural Computing Series. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-43631-8_14
Download citation
DOI: https://doi.org/10.1007/978-3-662-43631-8_14
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-43630-1
Online ISBN: 978-3-662-43631-8
eBook Packages: Computer ScienceComputer Science (R0)