Convergence analysis of recurrent neural network with self-loops based on eigenvalues of a connection matrix.
Yoshihiro TomikawaKenji NakayamaPublished in: ICNN (1995)
Keyphrases
- recurrent neural networks
- convergence analysis
- eigenvalues and eigenvectors
- covariance matrix
- global convergence
- singular value decomposition
- feed forward
- recurrent networks
- complex valued
- neural network
- optimality conditions
- reservoir computing
- echo state networks
- hidden layer
- artificial neural networks
- genetic algorithm
- approximation methods
- convergence rate
- convergence speed
- low level
- learning algorithm