We study the relationship between catastrophic forgetting and properties of task sequences. In particular, given a sequence of tasks, we would like to understand which properties of this …
In most machine learning algorithms, training data is assumed to be independent and identically distributed (iid). When it is not the case, the algorithm's performances are …
Continual Learning (CL) research typically focuses on tackling the phenomenon of catastrophic forgetting in neural networks. Catastrophic forgetting is associated with an …
H Zhao, T Zhou, G Long, J Jiang… - … on Machine Learning, 2023 - proceedings.mlr.press
Distribution shift (eg, task or domain shift) in continual learning (CL) usually results in catastrophic forgetting of previously learned knowledge. Although it can be alleviated by …
A large body of research in continual learning is devoted to overcoming the catastrophic forgetting of neural networks by designing new algorithms that are robust to the distribution …
Despite the growing interest in continual learning, most of its contemporary works have been studied in a rather restricted setting where tasks are clearly distinguishable, and task …
B Bagus, A Gepperth - 2021 International Joint Conference on …, 2021 - ieeexplore.ieee.org
Continual learning (CL) is a major challenge of machine learning (ML) and describes the ability to learn several tasks sequentially without catastrophic forgetting (CF). Recent works …
Standard artificial neural networks suffer from the well-known issue of catastrophic forgetting, making continual or lifelong learning difficult for machine learning. In recent years …
H Jin, E Kim - European Conference on Computer Vision, 2022 - Springer
When optimizing sequentially incoming tasks, deep neural networks generally suffer from catastrophic forgetting due to their lack of ability to maintain knowledge from old tasks. This …