Go ahead and do not forget: Modular lifelong learning from event-based data
Document Type
Article
Publication Date
8-1-2022
Abstract
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 eventbased 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. (c) 2022 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
Keywords
Lifelong learning, Habituation, Event-based data, Bio-inspired artificial intelligence
Divisions
ai
Funders
Alexander von Humboldt-Stiftung,Deutsche Forschungsgemeinschaft [Grant No; TRR169],Japan Society for the Promotion of Science
Publication Title
Neurocomputing
Volume
500
Publisher
Elsevier
Publisher Location
RADARWEG 29, 1043 NX AMSTERDAM, NETHERLANDS