Login / Signup

From Hope to Safety: Unlearning Biases of Deep Models via Gradient Penalization in Latent Space.

Maximilian DreyerFrederik PahdeChristopher J. AndersWojciech SamekSebastian Lapuschkin
Published in: AAAI (2024)
Keyphrases
  • latent space
  • prior knowledge
  • model selection
  • feature selection
  • active learning
  • probabilistic model
  • random variables
  • latent variables
  • lower dimensional