Variational Autoencoder (VAE) (optional)

Instructor of course: Prof. Mark Crowley
Teaching assistant and presenter of slides: Benyamin Ghojogh
Data and Knowledge Modeling and Analysis (ECE 657A) course
ECE Department, University of Waterloo, ON, Canada

This lecture includes:
1- Evidence Lower Bound (ELBO)
2- Expectation maximization
3- Encoder of variational autoencoder
4- decoder of variational autoencoder
5- Training variational autoencoder with expectation maximization
6- The reparameterization trick
7- Training variational autoencoder with backpropagation
8- Examples

Useful related resources:

1- Tutorial paper: Benyamin Ghojogh, Ali Ghodsi, Fakhri Karray, Mark Crowley. "Factor Analysis, Probabilistic Principal Component Analysis, Variational Inference, and Variational Autoencoder: Tutorial and Survey." arXiv preprint arXiv:2101.00734 (2021).

2- Tutorial YouTube videos by Carnegie Mellon University, Deep Learning:

3- Tutorial paper: Carl Doersch. "Tutorial on variational autoencoders." arXiv preprint arXiv:1606.05908 (2016).

4- Keras code for variational autoencoder:

[yousef.ghojogh]

Excellent, for the development of technical knowledge. I'm proud that you are my child. I am also very grateful to the university professors.