Models of hopfield-type clifford neural networks and their energy functions - hyperbolic and dual valued networks -

摘要: Recently, models of neural networks in the real domain have been extended into high dimensional such as complex and quaternion domain, several high-dimensional proposed. These extensions are generalized by introducing Clifford algebra (geometric algebra). In this paper we extend conventional real-valued recurrent defined discuss their dynamics. We present fully connected networks, which Hopfield type to algebra. study dynamics from point view existence conditions an energy function. derive function for two classes networks.