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 -