Autoencoders¶
Autoencoders (AE) are machines that encode inputs into a compact latent space.
Notation: dot ( )
We use a single vertically centered dot, i.e.,
A simple autoencoder can be achieved using two neural nets, e.g.,
where in this simple example,
is the encoder, and is the decoder.
For binary labels, we can use a simple cross entropy as the loss.
Code¶
See Lippe1.
-
Lippe P. Tutorial 9: Deep Autoencoders — UvA DL Notebooks v1.1 documentation. In: UvA Deep Learning Tutorials [Internet]. [cited 20 Sep 2021]. Available: https://uvadlc-notebooks.readthedocs.io/en/latest/tutorial_notebooks/tutorial9/AE_CIFAR10.html ↩
Contributors: