Chaining Meets Chain Rule: Multilevel Entropic Regularization and Training of Neural Networks.
Amir R. AsadiEmmanuel AbbePublished in: J. Mach. Learn. Res. (2020)
Keyphrases
- neural network
- training process
- training algorithm
- feed forward neural networks
- feedforward neural networks
- multi layer perceptron
- back propagation
- pattern recognition
- stochastic gradient descent
- early stopping
- neural network training
- backpropagation algorithm
- recurrent networks
- training phase
- multilayer perceptron
- test set
- training set
- fuzzy logic
- data sets
- fuzzy decision trees
- association rules
- training patterns
- artificial neural networks
- training examples
- fuzzy systems
- multi layer
- rule sets
- hidden layer
- regularization parameter
- supervised learning
- prior information
- activation function
- active learning
- rule learning
- information theory
- recurrent neural networks
- decision trees
- image processing
- neural network model