Skip to content
ml-recall

#reconstruction-loss

1 question from Autoencoders & VAEs

Timed test

1 question · 1 min · score and explanations at the end

Take a test
Q 1 / 1Score 0 / 0

Question 1: Single choice

easyAI-checkedAutoencoders & VAEs

You train a denoising autoencoder on MNIST by adding Gaussian noise to each batch, noisy = clip(images + 0.5 * randn). What do you feed into the model, and what do you compare its output with in the MSE loss?

Choose one option