R
Rahaf Aljundi
Researcher at Katholieke Universiteit Leuven
Publications - 38
Citations - 4548
Rahaf Aljundi is an academic researcher from Katholieke Universiteit Leuven. The author has contributed to research in topics: Forgetting & Task (project management). The author has an hindex of 17, co-authored 31 publications receiving 2242 citations. Previous affiliations of Rahaf Aljundi include University of Lyon & Centre national de la recherche scientifique.
Papers
More filters
Journal ArticleDOI
A continual learning survey: Defying forgetting in classification tasks.
Matthias Delange,Rahaf Aljundi,Marc Masana,Sarah Parisot,Xu Jia,Ales Leonardis,Greg Slabaugh,Tinne Tuytelaars +7 more
TL;DR: This work focuses on task incremental classification, where tasks arrive sequentially and are delineated by clear boundaries and study the influence of model capacity, weight decay and dropout regularization, and the order in which the tasks are presented, and qualitatively compare methods in terms of required memory, computation time and storage.
Book ChapterDOI
Memory Aware Synapses: Learning What (not) to Forget
TL;DR: This paper argues that, given the limited model capacity and the unlimited new information to be learned, knowledge has to be preserved or erased selectively and proposes a novel approach for lifelong learning, coined Memory Aware Synapses (MAS), which computes the importance of the parameters of a neural network in an unsupervised and online manner.
Posted Content
Memory Aware Synapses: Learning what (not) to forget
TL;DR: Memory Aware Synapses (MAS) as discussed by the authors computes the importance of the parameters of a neural network in an unsupervised and online manner, given a new sample which is fed to the network, accumulates an importance measure for each parameter, based on how sensitive the predicted output function is to a change in this parameter.
Posted Content
Gradient based sample selection for online continual learning
TL;DR: This work formulation of sample selection as a constraint reduction problem based on the constrained optimization view of continual learning shows that it is equivalent to maximizing the diversity of samples in the replay buffer with parameters gradient as the feature.
Proceedings ArticleDOI
Expert Gate: Lifelong Learning with a Network of Experts
TL;DR: In this article, the authors introduce a model of lifelong learning based on a Network of Experts, where new tasks / experts are learned and added to the model sequentially, building on what was learned before.