Train longer, generalize better: closing the generalization gap in large batch training of neural networks.
Elad HofferItay HubaraDaniel SoudryPublished in: NIPS (2017)
Keyphrases
- neural network
- training process
- training algorithm
- multi layer perceptron
- feed forward neural networks
- feedforward neural networks
- training patterns
- back propagation
- batch mode
- neural network training
- learning machines
- training stage
- backpropagation algorithm
- training set
- pattern recognition
- multilayer perceptron
- multi layer
- radial basis function network
- error back propagation
- multilayer neural network
- neural network model
- training samples
- supervised learning
- learning algorithm
- genetic algorithm
- training phase
- self organizing maps
- recurrent networks
- feature space
- case study