New results on recurrent network training: unifying the algorithms and accelerating convergence.
Amir F. AtiyaAlexander G. ParlosPublished in: IEEE Trans. Neural Networks Learn. Syst. (2000)
Keyphrases
- recurrent networks
- computational cost
- theoretical analysis
- benchmark datasets
- orders of magnitude
- convergence rate
- neural network
- learning algorithm
- training set
- stochastic approximation
- computational efficiency
- convergence analysis
- neural network training
- iterative algorithms
- recurrent neural networks
- significant improvement
- data structure
- data mining