In this lecture we will finish up our discussion of sparse coding and start our discussion of variational autoencoders (VAEs). VAEs are the first of the generative models that we will study. We will see how they modify the standard autoencoder reconstruction loss to create a well-defined generative model with clear probabilistic semantics.
Reference: (* = you are responsible for this material)
- *Sections 20.10.1-20.10.3 of the Deep Learning textbook.
- Diederik P Kingma, Max Welling, Auto-Encoding Variational Bayes published in the International Conference on Learning Representations (ICLR) 2014.
- Other reference are provided in the slides.