Sufficient Conditions for Error Backflow Convergence in Dynamical Recurrent Neural Networks.
Alex AussemPublished in: Neural Comput. (2002)
Keyphrases
- sufficient conditions
- recurrent neural networks
- linear complementarity problem
- neural network
- feed forward
- echo state networks
- recurrent networks
- fixed point
- exponential stability
- artificial neural networks
- cascade correlation
- asymptotic stability
- nonlinear dynamic systems
- linear systems
- neural model
- asymptotic optimality
- neuro fuzzy
- efficiently computable
- reservoir computing
- hidden layer
- convergence rate
- equilibrium point
- expert systems
- lyapunov function
- initial conditions
- linear programming
- fuzzy logic
- decision making