Keyphrases
- learning rate
- convergence rate
- convergence theorem
- rapid convergence
- convergence speed
- update rule
- adaptive learning rate
- error function
- weight update
- step size
- conjugate gradient algorithm
- multilayer neural networks
- learning algorithm
- global convergence
- weight vector
- hidden layer
- simulated annealing
- uniform convergence
- activation function
- training algorithm
- natural gradient
- feature vectors
- conjugate gradient
- particle swarm optimization