Training Recurrent Neural Networks by Sequential Least Squares and the Alternating Direction Method of Multipliers.
Alberto BemporadPublished in: CoRR (2021)
Keyphrases
- recurrent neural networks
- least squares
- echo state networks
- recurrent networks
- feedforward neural networks
- feed forward
- alternating direction method of multipliers
- neural network
- reservoir computing
- nonlinear dynamic systems
- training set
- convex optimization
- total variation
- artificial neural networks
- image sequences
- natural images
- multiscale
- learning algorithm