Cyclical Learning Rates (CLR'S) for Improving Training Accuracies and Lowering Computational Cost.
Rushikesh Ganesh ChopadeAditya StanamAnand NarayananShrikant D. PawarPublished in: IWBBIO (2) (2023)
Keyphrases
- learning rate
- computational cost
- backpropagation algorithm
- adaptive learning rate
- learning algorithm
- convergence rate
- feed forward neural networks
- hidden layer
- convergence speed
- gaussian kernels
- feedforward neural networks
- covering numbers
- training examples
- training samples
- back propagation
- training set
- upper bound
- supervised learning
- active learning
- uniform convergence
- machine learning