Monotonicity and convergence of asynchronous update gradient method for ridge polynomial neural network.
Xin YuLixia TangQingfeng ChenChenhua XuPublished in: Neurocomputing (2014)
Keyphrases
- gradient method
- convergence rate
- neural network
- step size
- convergence speed
- log likelihood function
- convex formulation
- learning rate
- back propagation
- optimization methods
- pattern recognition
- artificial neural networks
- negative matrix factorization
- information retrieval
- hidden layer
- nearest neighbor
- genetic algorithm
- optimization problems
- cost function
- multi objective
- multiresolution
- feature space
- face recognition