Skip to content
← All PyTorch tracks

Denoising Autoencoder Lab

PyTorch

Train an encoder and decoder to reconstruct clean patterns from noisy inputs.

Build · inspect · experiment

What you’ll build

  1. Compress noisy patterns through a small bottleneck.
  2. Backpropagate reconstruction error through both matrices.
  3. Inspect reconstructions and explore the latent space.

Prerequisites: Matrix multiplication, mean squared error and the chain rule. CPU-friendly; a GPU is optional.

Try the other framework →
0 / 1 solved
Start →
  1. 1. Not solved yet. Denoising Autoencoder Lab