Abstract
In this chapter, we answer the same question as in the last one, namely how many equilibria or fixed vectors the network has. The difference is that we have made a particular choice for the weight matrix, using the sum-of-outerproducts [60]. Because an extra restriction is imposed on the weight matrix, one expects to find a lower capacity, and we will see that this is indeed the case.
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
© 1997 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
De Wilde, P. (1997). Capacity from a Signal to Noise Ratio. In: Neural Network Models. Springer, London. https://doi.org/10.1007/978-1-84628-614-8_7
Download citation
DOI: https://doi.org/10.1007/978-1-84628-614-8_7
Publisher Name: Springer, London
Print ISBN: 978-3-540-76129-7
Online ISBN: 978-1-84628-614-8
eBook Packages: Springer Book Archive