Empirical study towards understanding line search approximations for training neural networks.
Younghwan ChaeDaniel N. WilkePublished in: CoRR (2019)
Keyphrases
- empirical studies
- line search
- neural network
- training algorithm
- conjugate gradient
- training process
- quadratic programming
- empirical analysis
- back propagation
- convergence rate
- risk minimization
- artificial neural networks
- fuzzy logic
- neural network model
- supervised learning
- primal dual
- radial basis function
- fault diagnosis
- linear programming
- hidden layer
- np hard
- levenberg marquardt
- global convergence
- training set