Accelerating Symmetric Rank-1 Quasi-Newton Method with Nesterov's Gradient for Training Neural Networks.
S. IndrapriyadarsiniShahrzad MahboubiHiroshi NinomiyaTakeshi KamioHideki AsaiPublished in: Algorithms (2022)
Keyphrases
- neural network
- quasi newton method
- training process
- training algorithm
- neural network training
- quasi newton
- back propagation
- training set
- artificial neural networks
- limited memory
- objective function
- semidefinite programming
- maximum margin
- multilayer perceptron
- differential evolution
- training samples
- support vector machine