Search Swinburne Research Bank
Please use this identifier to cite or link to this item: http://hdl.handle.net/1959.3/44069
|Download PDF (Published version) (Adobe Acrobat PDF, -1 bytes)|
- Binary output of cellular neural networks with smooth activation
- Andrew, Lachlan L. H.
- An important property of cellular neural networks (CNNs) is the binary output property, that, when the self-feedback is greater than one, the final activations are ۫ 1. This brief considers the generalization of this property to networks with sigmoidal output functions. It is shown that in this case the property cannot be stated without reference to the cross feedback, and conditions are found under which the property remains valid.
- Publication type
- Journal article
- IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications, Vol. 44, no. 9 (Sep 1997), pp. 821-824
- Publication year
- Binary associative memories; Binary image processing; Cellular neural networks; CNNs; Convergence of numerical methods; Eigenfunctions; Eigenvalues; Linearization; Matrix algebra; Transfer functions
- Publisher URL
- Copyright © 1997 IEEE. Paper reproduced here in accordance with the copyright policy of the publisher.
- Additional information
- This work was supported by a scholarship from the Australian Telecommunications and Electronics Research Board (ATERB).
- Full text
- Peer reviewed