Sitemap
Nerd For Tech

NFT is an Educational Media House. Our mission is to bring the invaluable knowledge and experiences of experts from all over the world to the novice. To know more about us, visit https://www.nerdfortech.org/.

Review — AAE: Adversarial Autoencoders (GAN)

6 min readApr 24, 2021

--

@ Medium)

Outline

1. AAE: Network Architecture

AAE: Network Architecture (+: Positive Samples, -: Negative Samples)

2. AAE vs VAE

AAE vs VAE on MNIST

3. Supervised AAE

Supervised AAE

4. Semi-Supervised AAE

Semi-Supervised AAE
Semi-supervised classification performance (error-rate) on MNIST and SVHN

5. Unsupervised AAE

Unsupervised clustering of MNIST using the AAE with 16 clusters
Unsupervised clustering performance (error-rate) of the AAE on MNIST

6. Dimension Reduction for Data Visualization Using AAE

Dimensionality reduction with adversarial autoencoders
Semi-Supervised and Unsupervised Dimensionality Reduction with AAE on MNIST.

Reference

Generative Adversarial Network (GAN)

My Other Previous Paper Readings

--

--

Nerd For Tech
Nerd For Tech

Published in Nerd For Tech

NFT is an Educational Media House. Our mission is to bring the invaluable knowledge and experiences of experts from all over the world to the novice. To know more about us, visit https://www.nerdfortech.org/.

Sik-Ho Tsang
Sik-Ho Tsang

Written by Sik-Ho Tsang

PhD, Researcher. I share what I learn. :) Linktree: https://linktr.ee/shtsang for Twitter, LinkedIn, etc.

No responses yet