Title :
Binary output of cellular neural networks with smooth activation
Author :
Andrew, Lachlan L H
Author_Institution :
Dept. of Electr. & Electron. Eng., Melbourne Univ., Parkville, Vic., Australia
fDate :
9/1/1997 12:00:00 AM
Abstract :
An important property of cellular neural networks (CNN´s) 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
Keywords :
cellular neural nets; recurrent neural nets; transfer functions; binary output property; cellular neural networks; cross feedback; final activations; self-feedback; sigmoidal output functions; smooth activation; Cellular neural networks; Neural network hardware; Neural networks; Neurofeedback; Neurons; Output feedback; Piecewise linear approximation; Piecewise linear techniques; State feedback; Vectors;
Journal_Title :
Circuits and Systems I: Fundamental Theory and Applications, IEEE Transactions on
