Controlling the Interaction Between Generation and Inference in Semi-Supervised Variational Autoencoders Using Importance Weighting.
Ghazi FelhiJoseph Le RouxDjamé SeddahPublished in: CoRR (2020)
Keyphrases
- semi supervised
- semi supervised learning
- denoising
- inference process
- labeled data
- semi supervised classification
- semi supervised clustering
- user interaction
- generation process
- neural network
- restricted boltzmann machine
- active learning
- belief networks
- subspace learning
- dirichlet process mixture models
- pairwise constraints
- tf idf
- graph cuts
- pairwise
- image sequences
- learning algorithm