Enhancing Classification of Energy Meters with Limited Labels using a Semi-Supervised Generative Model.
Chun FuHussain Syed KazmiMatias QuintanaClayton MillerPublished in: BuildSys@SenSys (2023)
Keyphrases
- generative model
- semi supervised
- unlabeled samples
- label information
- fully supervised
- discriminative learning
- semi supervised learning
- supervised learning
- pairwise
- unsupervised learning
- partially labeled
- label propagation
- labeled data
- class labels
- bayesian framework
- unlabeled data
- probabilistic model
- co training
- pairwise constraints
- training set
- supervised and unsupervised learning
- prior knowledge
- classification accuracy
- active learning
- em algorithm
- decision trees
- multi view
- sparse coding
- posterior probability
- support vector
- machine learning
- object categories
- model selection
- feature vectors
- hierarchical bayesian model
- generative and discriminative models
- unlabelled data
- labelled data
- training examples
- image processing
- learning algorithm