Title :
Non-monotone network dynamics; preliminary results
Author :
Trappenberg, Thomas
Author_Institution :
Canadian Complexity Centre, Hammonds Plains, NS, Canada
Abstract :
Recurrent neural networks with nonmonotone transfer functions have the interesting feature that they do not settle into a state if the start configuration is too far from the stored patterns. Instead, the network shows strong fluctuations. A first attempt to analyze the nature of this mode is made
Keywords :
nonmonotonic reasoning; recurrent neural nets; transfer functions; nonmonotone network dynamics; nonmonotone transfer functions; recurrent neural networks; start configuration; stored patterns; Artificial neural networks; Boolean functions; Chaos; Electronic mail; Fluctuations; Nonhomogeneous media; Psychology; Recurrent neural networks; Stochastic processes; Transfer functions;
Conference_Titel :
Neural Networks,1997., International Conference on
Conference_Location :
Houston, TX
Print_ISBN :
0-7803-4122-8
DOI :
10.1109/ICNN.1997.616129
