Chaining Meets Chain Rule: Multilevel Entropic Regularization and Training of Neural Nets.
Amir R. AsadiEmmanuel AbbePublished in: CoRR (2019)
Keyphrases
- neural nets
- feed forward
- supervised training
- back propagation
- neural network
- multi layer
- artificial neural networks
- training algorithm
- backpropagation neural networks
- early stopping
- training phase
- feed forward neural networks
- learning tasks
- hidden layer
- counter propagation
- feedforward neural networks
- stochastic gradient descent
- training set
- deep architectures
- training examples
- supervised learning
- expert systems
- decision making
- information retrieval