Training recurrent network with block-diagonal approximated Levenberg-Marquardt algorithm.
Lai-Wan ChanChi-Cheong SzetoPublished in: IJCNN (1999)
Keyphrases
- levenberg marquardt
- training algorithm
- least squares
- artificial neural networks
- back propagation
- block diagonal
- recurrent networks
- bundle adjustment
- optimal solution
- np hard
- objective function
- neural network
- training process
- learning algorithm
- principal component analysis
- closed form
- semidefinite programming
- genetic algorithm