An Efficient Approach for Parameters Learning of Bayesian Network with Multiple Latent Variables Using Neural Networks and P-EM.
Kaiyu SongKun YueXinran WuJia HaoPublished in: CollaborateCom (1) (2020)
Keyphrases
- latent variables
- parameter learning
- neural network
- hidden variables
- probabilistic model
- latent variable models
- bayesian networks
- prior knowledge
- maximum likelihood
- structured prediction
- structural svms
- structured output
- max margin
- learning problems
- random variables
- posterior distribution
- expectation maximization
- supervised learning
- learning algorithm
- machine learning
- knowledge discovery
- active learning
- high dimensional
- observed variables