Pre-training the deep generative models with adaptive hyperparameter optimization.
Chengwei YaoDeng CaiJiajun BuGencai ChenPublished in: Neurocomputing (2017)
Keyphrases
- generative model
- deep belief networks
- discriminative learning
- probabilistic model
- mixture model
- discriminatively trained
- hierarchical hidden markov models
- bayesian framework
- maximum entropy principle
- prior knowledge
- discriminative models
- em algorithm
- restricted boltzmann machine
- hyperparameters
- semi supervised
- topic models
- generative and discriminative models
- conditional random fields
- structured prediction
- model selection
- training set
- image processing
- representational power
- graphical models
- discriminative methods
- supervised learning
- object detection