An efficient MLP-learning algorithm using parallel tangent gradient and improved adaptive learning rates.
Payman MoallemS. Amirhassan MonadjemiPublished in: Connect. Sci. (2010)
Keyphrases
- learning rate
- learning algorithm
- activation function
- bp algorithm
- convergence rate
- hidden layer
- multilayer perceptron
- back propagation
- convergence speed
- neural network
- rbf network
- weight vector
- gaussian kernels
- uniform convergence
- machine learning algorithms
- artificial neural networks
- covering numbers
- machine learning
- multi objective
- active learning
- lower bound
- training data
- sample complexity
- learning tasks
- special case
- convergence theorem
- delta bar delta