A family of discriminative training criteria based on the F-divergence for deep neural networks.
Markus Nußbaum-ThomXiaodong CuiRalf SchlüterVaibhava GoelHermann NeyPublished in: ICASSP (2014)
Keyphrases
- discriminative training
- neural network
- hidden markov models
- probabilistic interpretation
- maximum likelihood
- pattern recognition
- posterior probability
- support vector machine
- fuzzy logic
- automatic speech recognition
- discriminatively trained
- co training
- unsupervised learning
- minimum classification error
- training process
- object detection
- d objects
- preprocessing
- machine learning