Title :
Generalization of CNN with hysteresis nonlinearity
Author_Institution :
Dept. of Math., Univ. of Min. & Geol., Sofia, Bulgaria
Abstract :
We introduce a general class of neural networks. This new model covers some of the known neural network architectures, including cellular neural networks and Hopfield networks. Hysteresis feedback networks are introduced and compared to the general Hopfield networks in order to prove the existence of hysteresis phenomena in the network
Keywords :
cellular neural nets; differential equations; feedback; generalisation (artificial intelligence); hysteresis; Hopfield networks; cellular neural networks; differential equation; feedback; generalization; hysteresis; nonlinearity; Cellular neural networks; Differential equations; Geology; Hopfield neural networks; Hysteresis; Mathematics; Neural networks; Neurofeedback; Nonlinear circuits; Nonlinear equations;
Conference_Titel :
Cellular Neural Networks and Their Applications Proceedings, 1998 Fifth IEEE International Workshop on
Conference_Location :
London
Print_ISBN :
0-7803-4867-2
DOI :
10.1109/CNNA.1998.685330
