arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2107.12657cs.LGcs.CV
收藏

具有神经元激活重要性的持续学习

Continual Learning with Neuron Activation Importance

Kyunghee University(庆熙大学)

Sohee Kim, Seungkyu Lee

摘要:

持续学习是一种具有多个顺序任务的在线学习的概念。持续学习的关键障碍之一是网络学习新任务时需要保留旧任务的知识,而不需要访问旧任务的任何数据。在本文中,我们提出了一种基于神经元激活重要性的正则化方法,用于稳定的持续学习,而不管任务的顺序。我们在现有的基准数据集上进行了全面的实验,不仅评估了我们的方法的稳定性和可塑性,提高了分类精度,而且还评估了任务顺序变化时性能的鲁棒性。

英文摘要:

Continual learning is a concept of online learning with multiple sequential tasks. One of the critical barriers of continual learning is that a network should learn a new task keeping the knowledge of old tasks without access to any data of the old tasks. In this paper, we propose a neuron activation importance-based regularization method for stable continual learning regardless of the order of tasks. We conduct comprehensive experiments on existing benchmark data sets to evaluate not just the stability and plasticity of our method with improved classification accuracy also the robustness of the performance along the changes of task order.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑