0Pricing
Deep Learning Academy · Lesson

Denoising Autoencoders

Reconstruct clean data from corrupted input.

From Copying to Cleaning

A plain autoencoder rebuilds its input. A denoising autoencoder goes further: you feed it a corrupted version and ask it to restore the clean original.

Add Noise on Purpose

You deliberately damage the input with noise before feeding it in. The clean original stays as the target the network must reach.

noisy = clean + 0.3 * torch.randn_like(clean)

All lessons in this course

  1. Encoder, Bottleneck & Decoder
  2. Denoising Autoencoders
  3. Variational Autoencoders & the Latent Space
  4. Anomaly Detection by Reconstruction Error
← Back to Deep Learning Academy