.png){kind=icon}
返回
Lifelong Learning With Cycle Memory Networks
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2023.3294495.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Learning from a sequence of tasks for a lifetime is essential for an agent toward artificial general intelligence. Despite the explosion of this research field in recent years, most work focuses on the well-known catastrophic forgetting issue. In contrast, this work aims to explore knowledge-transferable lifelong learning without storing historical data and significant additional computational overhead. We demonstrate that existing data-free frameworks, including regularization-based single-network and structure-based multinetwork frameworks, face a fundamental issue of lifelong learning, named anterograde forgetting, i.e., preserving and transferring memory may inhibit the learning of new knowledge. We attribute it to the fact that the learning network capacity decreases while memorizing historical knowledge and conceptual confusion between the irrelevant old knowledge and the current task. Inspired by the complementary learning theory in neuroscience, we endow artificial neural networks with the ability to continuously learn without forgetting while recalling historical knowledge to facilitate learning new knowledge. Specifically, this work proposes a general framework named cycle memory networks (CMNs). The CMN consists of two individual memory networks to store short- and long-term memories separately to avoid capacity shrinkage and a transfer cell between them. It enables knowledge transfer from the long-term to the short-term memory network to mitigate conceptual confusion. In addition, the memory consolidation mechanism integrates short-term knowledge into the long-term memory network for knowledge accumulation. We demonstrate that the CMN can effectively address the anterograde forgetting on several task-related, task-conflict, class-incremental, and cross-domain benchmarks. Furthermore, we provide extensive ablation studies to verify each framework component. The source codes are available at: https://github.com/GeoX-Lab/CMN.
Keyword:
Task analysis
Knowledge engineering
Learning (artificial intelligence)
Learning systems
Neuroscience
Microprocessors
Knowledge transfer
Anterograde forgetting
catastrophic forgetting
complementary learning theory
cycle memory network (CMN)
lifelong learning
期刊
IF:
8.9
论文数:
7.6K
被引数:
7.2W
机构
引用论文
分享收藏
分享收藏WHY THERE ARE COMPLEMENTARY LEARNING-SYSTEMS IN THE HIPPOCAMPUS AND NEOCORTEX - INSIGHTS FROM THE SUCCESSES AND FAILURES OF CONNECTIONIST MODELS OF LEARNING AND MEMORY为什么在海马和新大脑皮层中存在互补的学习系统-来自学习和记忆的连接主义模型的成功和失败的见解.png)
PSYCHOLOGICAL REVIEW
PSYCHOLOGICAL REVIEWIF5.8
PREAI
分享收藏
查看更多内容