Training convolutional networks with weight-wise adaptive learning rates.
Alan MoscaGeorge D. MagoulasPublished in: ESANN (2017)
Keyphrases
- learning rate
- adaptive learning rate
- backpropagation algorithm
- weight vector
- learning algorithm
- convergence rate
- feed forward neural networks
- pairwise
- gaussian kernels
- hidden layer
- neural network
- restricted boltzmann machine
- convergence speed
- back propagation
- convergence theorem
- training set
- feedforward neural networks
- uniform convergence
- covering numbers
- learning theory
- optimal solution
- artificial neural networks