Investigations on hessian-free optimization for cross-entropy training of deep neural networks.
Simon WieslerJinyu LiJian XuePublished in: INTERSPEECH (2013)
Keyphrases
- cross entropy
- neural network
- training process
- training algorithm
- feedforward neural networks
- maximum likelihood
- log likelihood
- error function
- training set
- multi layer perceptron
- neural network model
- back propagation
- network architecture
- artificial neural networks
- multilayer perceptron
- neural nets
- training phase
- supervised learning
- evolutionary algorithm
- density estimation
- language modeling
- ranking functions
- mutual information
- image registration