27 citations · 44 across the 22 of their papers we have counts for
3 papers · 1 filter
Read Between the Layers: Leveraging Multi-Layer Representations for Rehearsal-Free Continual Learning with Pre-Trained Models
Kyra Ahrens, Hans Hergen Lehmann, Jae Hee Lee +1
We address the Continual Learning (CL) problem, wherein a model must learn a sequence of tasks from non-stationary distributions while preserving prior knowledge upon encountering…
Visually Grounded Continual Language Learning with Selective Specialization
Kyra Ahrens, Lennart Bengtson, Jae Hee Lee +1
A desirable trait of an artificial agent acting in the visual world is to continually learn a sequence of language-informed tasks while striking a balance between sufficiently spec…
From Neural Activations to Concepts: A Survey on Explaining Concepts in Neural Networks
Jae Hee Lee, Sergio Lanza, Stefan Wermter
In this paper, we review recent approaches for explaining concepts in neural networks. Concepts can act as a natural link between learning and reasoning: once the concepts are iden…