A diagonally scaled Newton-type proximal method for minimization of the models with nonsmooth composite cost functions.
Zohre AminifardSaman Babaie-KafakiPublished in: Comput. Appl. Math. (2023)
Keyphrases
- cost function
- objective function
- probabilistic model
- preprocessing
- segmentation method
- support vector machine
- newton method
- dynamic programming
- significant improvement
- neural network
- high accuracy
- detection method
- prior knowledge
- statistical methods
- parametric models
- em algorithm
- statistical model
- learning algorithm