All terms

Autoencoder

A neural network trained to compress input into a latent code and reconstruct it — useful for representation learning and anomaly detection.

Deep Learning1 min read

Definition

An autoencoder has an encoder that maps input to a lower-dimensional latent vector and a decoder that reconstructs the input. Training minimizes reconstruction error.

Variants include denoising, variational (VAE), and sparse autoencoders.

In simple terms

Summarize a book into bullet notes (encode), then rewrite the book from those notes (decode). Good notes capture what mattered.

Where you see it

  • Anomaly detection when reconstruction fails on odd inputs.
  • Dimensionality reduction and feature learning.
  • VAEs for generative modeling.

How it works

  1. 1.Encode

    Compress input to latent representation.

  2. 2.Decode

    Reconstruct from the latent code.

  3. 3.Minimize error

    Train so reconstruction matches the original.

Why it matters

  • Autoencoders teach representation learning — a stepping stone to modern generative models.

Often confused

  • Autoencoders are just for compression like ZIP.

    They learn semantic latents for ML tasks, not bit-perfect file compression.