Abstract
In this chapter, we will develop and investigate the negative feedback network. We will, in fact, develop an extremely simple and effective Principal Component network which needs no weight decay in its learning rule: because of the negative feedback of activation, we can use simple Hebbian learning which will not cause instability in the weight growth process and which moreover causes the weights to converge to the Principal Components of the input data. We will show that the network can be used to extract both principal and minor components.
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.
Rights and permissions
Copyright information
© 2005 Springer-Verlag London Limited
About this chapter
Cite this chapter
(2005). The Negative Feedback Network. In: Hebbian Learning and Negative Feedback Networks. Advanced Information and Knowledge Processing. Springer, London. https://doi.org/10.1007/1-84628-118-0_3
Download citation
DOI: https://doi.org/10.1007/1-84628-118-0_3
Publisher Name: Springer, London
Print ISBN: 978-1-85233-883-1
Online ISBN: 978-1-84628-118-1
eBook Packages: Computer ScienceComputer Science (R0)