Optimizing neural network hyperparameters with Gaussian processes for dialog act classification.
Franck DernoncourtJi Young LeePublished in: SLT (2016)
Keyphrases
- gaussian processes
- hyperparameters
- model selection
- gaussian process
- support vector
- cross validation
- bayesian methods
- covariance function
- incremental learning
- bayesian framework
- gaussian process regression
- closed form
- bayesian inference
- em algorithm
- incomplete data
- maximum a posteriori
- sample size
- maximum likelihood
- random sampling
- machine learning
- feature selection
- supervised learning
- support vector machine
- noise level
- training set
- decision trees
- regression model
- missing data
- machine learning algorithms
- expectation maximization
- text classification
- markov random field
- multi task
- worst case
- learning process
- feature space
- reinforcement learning