Representation Learning · Intermediate

Autoencoder

Compress inputs through a tiny bottleneck and watch genuine reconstructions improve.

A tiny autoencoder teaches encoder, latent bottleneck, decoder, and reconstruction learning.

Step by step

  1. Encode the input.
  2. Pass through a latent bottleneck.
  3. Decode the latent value.
  4. Measure reconstruction error.
  5. Backpropagate decoder and encoder gradients.

Core formulas

Encoder

z = tanh(W_e x + b_e)

The input is compressed into a bottleneck.

Reconstruction loss

L = ½||x̂−x||²

Training reduces reconstruction error.

When to use Autoencoder

  • Learning representation learning and bottlenecks.

Official documentation

TensorFlow Autoencoder tutorial