Delayed Recurrent Neural Networks with Global Lipschitz Activation Functions
It is well known that activation functions of RNNs are important characters of RNNs. Usually, activation functions are nonlinear functions, thus they make RNNs be described by nonlinear systems. Since they represent some structural parts of the the nonlinear systems, they crucially decide the dynamical properties of RNNs.
KeywordsPeriodic Solution Equilibrium Point Activation Function Convergence Analysis Recurrent Neural Network
Unable to display preview. Download preview PDF.