2 citations · 5 across the 6 of their papers we have counts for
6 papers
Forgetting, plasticity, and co-observation: a third facet of continual learning
Timm Hess, Abhishek Jha, Gido M. van de Ven +1
Efficient continual learning remains a fundamental challenge for deep neural networks. While catastrophic forgetting and loss of plasticity are widely considered the primary obstac…
Position: Modular Memory is the Key to Continual Learning Agents
Vaggelis Dorovatas, Malte Schwerin, Andrew D. Bagdanov +21
Foundation models have transformed machine learning through large-scale pretraining and increased test-time compute. Despite surpassing human performance in several domains, these…
Forgetting of task-specific knowledge in model merging-based continual learning
Timm Hess, Gido M van de Ven, Tinne Tuytelaars
This paper investigates the linear merging of models in the context of continual learning (CL). Using controlled visual cues in computer vision experiments, we demonstrate that mer…
Two Complementary Perspectives to Continual Learning: Ask Not Only What to Optimize, But Also How
Timm Hess, Tinne Tuytelaars, Gido M. van de Ven
Recent years have seen considerable progress in the continual training of deep neural networks, predominantly thanks to approaches that add replay or regularization terms to the lo…
Knowledge Accumulation in Continually Learned Representations and the Issue of Feature Forgetting
Timm Hess, Eli Verwimp, Gido M. van de Ven +1
Continual learning research has shown that neural networks suffer from catastrophic forgetting "at the output level", but it is debated whether this is also the case at the level o…
A Procedural World Generation Framework for Systematic Evaluation of Continual Learning
Timm Hess, Martin Mundt, Iuliia Pliushch +1
Several families of continual learning techniques have been proposed to alleviate catastrophic interference in deep neural network training on non-stationary data. However, a compr…