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. 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 continuous learning. Furthermore, we introduce a habituation-based method to mitigate forgetting. Our experimental results show that the combination of different techniques can help to avoid catastrophic forgetting while learning incrementally from the features provided by the extraction module.
@article{arxiv.2111.08458,
title = {Lifelong Learning from Event-based Data},
author = {Vadym Gryshchuk and Cornelius Weber and Chu Kiong Loo and Stefan Wermter},
journal= {arXiv preprint arXiv:2111.08458},
year = {2021}
}
Comments
In Proceedings of the 29th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning