← Lessons

quiz vs the machine

Gold1390

Machine Learning

Autoencoders

Networks that learn to compress data and rebuild it from the compression.

5 min read · core · beat Gold to climb

What it is

An autoencoder is a network trained to copy its input to its output through a narrow middle. By forcing the data through a small bottleneck, it learns a compact representation called the latent code.

Two halves

An autoencoder is built from two stacked networks.

  • The encoder maps the input down to a low dimensional latent code
  • The decoder maps the latent code back up to a reconstruction of the input

Training minimizes a reconstruction loss, the difference between the input and the rebuilt output. No labels are needed, so this is self supervised learning.

What it learns and uses

The bottleneck is the whole point. It cannot store everything, so it must keep only the most useful structure.

  • The latent code works as a learned dimensionality reduction
  • A denoising autoencoder is fed corrupted input and must rebuild the clean version, which yields robust features
  • Trained autoencoders also power anomaly detection, since rare inputs reconstruct poorly and produce high error

Key idea

An autoencoder squeezes data through a bottleneck and rebuilds it, learning a compact representation without labels.

Check yourself

Answer to earn rating on the learn ladder.

1. What loss does a basic autoencoder minimize?

2. Why can autoencoders flag anomalies?