Train longer, generalize better: closing the generalization gap in large batch training of neural networks.
Elad HofferItay HubaraDaniel SoudryPublished in: CoRR (2017)
Keyphrases
- neural network
- training algorithm
- training process
- feed forward neural networks
- artificial neural networks
- batch mode
- learning machines
- pattern recognition
- neural network training
- backpropagation algorithm
- training stage
- feedforward neural networks
- training patterns
- back propagation
- multi layer perceptron
- error back propagation
- multi layer
- feed forward
- neural network structure
- fuzzy logic
- radial basis function network
- training examples
- training phase
- training set
- neural network model
- recurrent networks
- training data
- genetic algorithm
- online learning
- batch processing
- recurrent neural networks
- activation function
- fuzzy systems
- data sets