Normalized Stochastic Gradient Descent Training of Deep Neural Networks.
Salih AticiHongyi PanAhmet Enis ÇetinPublished in: CoRR (2022)
Keyphrases
- stochastic gradient descent
- neural network
- early stopping
- loss function
- least squares
- step size
- matrix factorization
- training speed
- training process
- random forests
- support vector machine
- training algorithm
- online algorithms
- regularization parameter
- back propagation
- multiple kernel learning
- importance sampling
- weight vector
- cost function
- genetic algorithm
- semi supervised learning
- linear svm
- learning algorithm