.png){kind=icon}
返回
Is Class-Incremental Enough for Continual Learning?
.png){kind=icon}
OA
AI
DOI：10.3389/frai.2022.829842.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The ability of a model to learn continually can be empirically assessed in different continual learning scenarios. Each scenario defines the constraints and the opportunities of the learning environment. Here, we challenge the current trend in the continual learning literature to experiment mainly on class-incremental scenarios, where classes present in one experience are never revisited. We posit that an excessive focus on this setting may be limiting for future research on continual learning, since class-incremental scenarios artificially exacerbate catastrophic forgetting, at the expense of other important objectives like forward transfer and computational efficiency. In many real-world environments, in fact, repetition of previously encountered concepts occurs naturally and contributes to softening the disruption of previous knowledge. We advocate for a more in-depth study of alternative continual learning scenarios, in which repetition is integrated by design in the stream of incoming information. Starting from already existing proposals, we describe the advantages such class-incremental with repetition scenarios could offer for a more comprehensive assessment of continual learning models.
Keyword:
continual learning
lifelong learning
catastrophic forgetting
class-incremental
class-incremental with repetition
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
F
IF:
4.7
论文数:
2.4K
被引数:
4.4K
机构
引用论文
Continual learning for robotics: Definition, framework, learning strategies, opportunities and challenges机器人持续学习: 定义、框架、学习策略、机遇与挑战.png)
INFORMATION FUSIONOAAI
INFORMATION FUSIONIF15.5
OAAI分享收藏Continual learning for recurrent neural networks: An empirical evaluation递归神经网络的持续学习: 经验评估NEURAL NETWORKSOAAI
NEURAL NETWORKSIF6.3
OAAI分享收藏分享收藏分享收藏
查看更多内容