Continual Lifelong Learning with Neural Networks: A Review
German I. Parisi1, Ronald Kemker2, Jose L. Part3, Christopher Kanan2, Stefan Wermter1 1Knowledge Technology, Department of Informatics, Universität Hamburg, Germany 2Chester F. Carlson Center for Imaging Science, Rochester Institute of Technology, NY, USA 3Department of Computer Science, Heriot-Watt University, Edinburgh Centre for Robotics, Scotland, UK
Abstract
Humans and animals have the ability to continually acquire, fine-tune, and transfer knowledge and skills throughout their lifespan. This ability, referred to as lifelong learning, is mediated by a rich set of neurocognitive mechanisms that together contribute to the development and specialization of our sensorimotor skills as well as to long-term memory consolidation and retrieval. Consequently, lifelong learning capabilities are crucial for computational systems and autonomous agents interacting in the real world and processing continuous streams of information. However, lifelong learning remains a long-standing challenge for machine learning and neural network models since the continual acquisition of incrementally available information from non-stationary data distributions generally leads to catastrophic forgetting or interference. This limitation represents a major drawback for state-of-the-art deep neural network models that typically learn representations from stationary batches of training data, thus without accounting for situations in which information becomes incrementally available over time. In this review, we critically summarize the main challenges linked to lifelong
中文速览
机器学习系统在持续学习新任务时会"灾难性遗忘（catastrophic forgetting）"先前掌握的知识，这一顽固难题严重制约着自主智能体在真实世界中的应用。这篇综述系统梳理了大脑终身学习的神经认知机制——包括突触可塑性、海马体记忆回放、课程学习、迁移学习、内在动机和多感官整合——并以此为参照，全面比较了当前缓解灾难性遗忘的三类主流神经网络方法：通过正则化约束突触权重变化、动态扩展网络结构、以及借鉴互补学习系统（Complementary Learning Systems）进行经验重放。作者发现，尽管各类方法在受控的单模态分类任务上取得了显著进展，但距离能在开放环境中自主、持续、多模态学习的智能体仍有相当大的差距，现有评估指标和基准也亟待完善。这项工作的价值在于为跨越生物学与人工智能的终身学习研究提供了系统性的路线图，指出了通往更鲁棒、更类脑的持续学习系统所需突破的关键方向。
原文 arXiv:1802.07569;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1802.07569v4