Title :
Dynamical properties of neural nets using competitive activation mechanisms
Author :
Benaim, M. ; Samuelides, Manuel
Abstract :
It is shown that layered feedforward nets are convergent, while nonperiodic oscillations might occur in bidirectional nets. The virtual lateral inhibition phenomenon in feedforward nets is discussed. It is shown that a certain kind of nonlinearity in output functions may be successfully used in realizing winner-take-all networks
Keywords :
learning systems; neural nets; Lyapounov function; bidirectional nets; competitive activation mechanisms; competitive learning; convergence; layered feedforward nets; neural nets; nonlinearity; nonperiodic oscillations; output functions; virtual lateral inhibition phenomenon; winner-take-all networks;
Conference_Titel :
Neural Networks, 1990., 1990 IJCNN International Joint Conference on
Conference_Location :
San Diego, CA, USA
DOI :
10.1109/IJCNN.1990.137896
