A New Algorithm with a Line Search for Feedforward Neural Networks Training.
Jaroslaw BilskiBartosz KowalczykJacek M. ZuradaPublished in: ICAISC (1) (2020)
Keyphrases
- feedforward neural networks
- convergence rate
- k means
- line search
- training process
- learning algorithm
- cost function
- dynamic programming
- expectation maximization
- optimization algorithm
- training phase
- training algorithm
- objective function
- step size
- recurrent neural networks
- back propagation
- simulated annealing
- conjugate gradient
- least squares