Three types of incremental learning
| dc.citation.firstpage | 1185 | en_US |
| dc.citation.journalTitle | Nature Machine Intelligence | en_US |
| dc.citation.lastpage | 1197 | en_US |
| dc.citation.volumeNumber | 4 | en_US |
| dc.contributor.author | van de Ven, Gido M. | en_US |
| dc.contributor.author | Tuytelaars, Tinne | en_US |
| dc.contributor.author | Tolias, Andreas S. | en_US |
| dc.date.accessioned | 2023-01-27T14:47:40Z | en_US |
| dc.date.available | 2023-01-27T14:47:40Z | en_US |
| dc.date.issued | 2022 | en_US |
| dc.description.abstract | Incrementally learning new information from a non-stationary stream of data, referred to as ‘continual learning’, is a key feature of natural intelligence, but a challenging problem for deep neural networks. In recent years, numerous deep learning methods for continual learning have been proposed, but comparing their performances is difficult due to the lack of a common framework. To help address this, we describe three fundamental types, or ‘scenarios’, of continual learning: task-incremental, domain-incremental and class-incremental learning. Each of these scenarios has its own set of challenges. To illustrate this, we provide a comprehensive empirical comparison of currently used continual learning strategies, by performing the Split MNIST and Split CIFAR-100 protocols according to each scenario. We demonstrate substantial differences between the three scenarios in terms of difficulty and in terms of the effectiveness of different strategies. The proposed categorization aims to structure the continual learning field, by forming a key foundation for clearly defining benchmark problems. | en_US |
| dc.identifier.citation | van de Ven, Gido M., Tuytelaars, Tinne and Tolias, Andreas S.. "Three types of incremental learning." <i>Nature Machine Intelligence,</i> 4, (2022) Springer Nature: 1185-1197. https://doi.org/10.1038/s42256-022-00568-3. | en_US |
| dc.identifier.digital | s42256-022-00568-3 | en_US |
| dc.identifier.doi | https://doi.org/10.1038/s42256-022-00568-3 | en_US |
| dc.identifier.uri | https://hdl.handle.net/1911/114299 | en_US |
| dc.language.iso | eng | en_US |
| dc.publisher | Springer Nature | en_US |
| dc.rights | This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. | en_US |
| dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | en_US |
| dc.title | Three types of incremental learning | en_US |
| dc.type | Journal article | en_US |
| dc.type.dcmi | Text | en_US |
| dc.type.publication | publisher version | en_US |
Files
Original bundle
1 - 1 of 1