To cope with real-world dynamics, an intelligent system needs to incrementally acquire,
update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as …

Forgetting refers to the loss or deterioration of previously acquired knowledge. While
existing surveys on forgetting have primarily focused on continual learning, forgetting is a …

A recent trend in artificial intelligence is the use of pretrained models for language and
vision tasks, which have achieved extraordinary performance but also puzzling failures …

How to balance the learning'sensitivity-stability'upon new task training and memory
preserving is critical in CL to resolve catastrophic forgetting. Improving model generalization …

Deep learning is increasingly moving towards a transfer learning paradigm whereby large
foundation models are fine-tuned on downstream tasks, starting from an initialization …

Bayesian deep learning seeks to equip deep neural networks with the ability to precisely
quantify their predictive uncertainty, and has promised to make deep learning more reliable …

Parameter-space regularization in neural network optimization is a fundamental tool for
improving generalization. However, standard parameter-space regularization methods …

Reliable predictive uncertainty estimation plays an important role in enabling the
deployment of neural networks to safety-critical settings. A popular approach for estimating …

Standard regularized training procedures correspond to maximizing a posterior distribution
over parameters, known as maximum a posteriori (MAP) estimation. However, model …

Bayesian optimization is a highly efficient approach to optimizing objective functions which
are expensive to query. These objectives are typically represented by Gaussian process …