Convergence of Batch Gradient Method for Training of Pi-Sigma Neural Network with Regularizer and Adaptive Momentum Term.
Qinwei FanLe LiuQian KangLi ZhouPublished in: Neural Process. Lett. (2023)
Keyphrases
- gradient method
- convergence rate
- neural network
- learning rate
- training error
- training process
- convergence speed
- step size
- regularization term
- hidden layer
- fermentation process
- artificial neural networks
- optimization methods
- training set
- back propagation
- semi supervised
- cost function
- multi objective
- negative matrix factorization
- actor critic
- convex formulation
- objective function
- image processing