Closing the gap: Exact maximum likelihood training of generative autoencoders using invertible layers.
Gianluigi SilvestriDaan RoosLuca AmbrogioniPublished in: CoRR (2022)
Keyphrases
- maximum likelihood
- discriminative training
- deep belief networks
- feedforward neural networks
- unsupervised learning
- denoising
- generative model
- discriminatively trained
- data driven
- likelihood function
- training examples
- training process
- training phase
- test set
- synthetic aperture radar
- machine learning
- expectation maximization
- training set