Variational Beam Search for Novelty Detection

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Posterior Meta-Replay for Continual Learning (2021, background): “Therefore, Li et al. [40] suggest to broaden this prior by tempering the current prior p ( W ) when task boundaries are detected: p β ( W ) ≡ 1 Z β p ( W ) β , with inverse temperature β and normalization Z β .”