Variational Autoencoding (VAE) System

A Variational Autoencoding (VAE) System is an autoencoding system that implements a VAE algorithm to solve a VAE task.

• Example(s):
  • https://github.com/pytorch/examples/tree/master/vae
• See: GAN System, Adam Stochastic Optimization Algorithm.

---

---

References

2018

• https://github.com/pytorch/examples/blob/master/vae/README.md
  • QUOTE: This is an improved implementation of the paper Stochastic Gradient VB and the Variational Auto-Encoder by Kingma and Welling. It uses ReLUs and the adam optimizer, instead of sigmoids and adagrad. These changes make the network converge much faster.

---