Go ahead and do not forget: Modular lifelong learning from event-based data
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Go ahead and do not forget: Modular lifelong learning from event-based data. / Gryshchuk, Vadym; Weber , Cornelius; Loo, Chu Kiong ; Wermter, Stefan .
In: Neurocomputing, Vol. 500, 01.06.2022, p. 1063-1074.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Go ahead and do not forget: Modular lifelong learning from event-based data
AU - Gryshchuk, Vadym
AU - Weber , Cornelius
AU - Loo, Chu Kiong
AU - Wermter, Stefan
PY - 2022/6/1
Y1 - 2022/6/1
N2 - Lifelong learning is a long-standing aim for artificial agents that act in dynamic environments in which an agent needs to accumulate knowledge incrementally without forgetting previously learned representations. Contemporary methods for incremental learning from images are predominantly based on frame-based data recorded by conventional shutter cameras. We investigate methods for learning from data produced by event cameras and compare techniques to mitigate forgetting while learning incrementally. We propose a model that is composed of both, feature extraction and incremental learning. The feature extractor is utilized as a self-supervised sparse convolutional neural network that processes event-based data. The incremental learner uses a habituation-based method that works in tandem with other existing techniques. Our experimental results show that the combination of different existing techniques with our proposed habituation-based method can help avoid catastrophic forgetting even more, while learning incrementally from the features provided by the extraction module.
AB - Lifelong learning is a long-standing aim for artificial agents that act in dynamic environments in which an agent needs to accumulate knowledge incrementally without forgetting previously learned representations. Contemporary methods for incremental learning from images are predominantly based on frame-based data recorded by conventional shutter cameras. We investigate methods for learning from data produced by event cameras and compare techniques to mitigate forgetting while learning incrementally. We propose a model that is composed of both, feature extraction and incremental learning. The feature extractor is utilized as a self-supervised sparse convolutional neural network that processes event-based data. The incremental learner uses a habituation-based method that works in tandem with other existing techniques. Our experimental results show that the combination of different existing techniques with our proposed habituation-based method can help avoid catastrophic forgetting even more, while learning incrementally from the features provided by the extraction module.
U2 - 10.1016/j.neucom.2022.05.101
DO - 10.1016/j.neucom.2022.05.101
M3 - Journal article
VL - 500
SP - 1063
EP - 1074
JO - Neurocomputing
JF - Neurocomputing
SN - 0925-2312
ER -
ID: 311616437