Deep Generative Dual Memory Network for Continual Learning
Nitin Kamra Umang Gupta Yan Liu
Abstract
Despite advances in deep learning, neural networks can only learn multiple tasks when trained on them jointly. When tasks arrive sequentially, they lose performance on previously learnt tasks. This phenomenon called catastrophic forgetting is a fundamental challenge to overcome before neural networks can learn continually from incoming data. In this work, we derive inspiration from human memory to develop an architecture capable of learning continuously from sequentially incoming tasks, while averting catastrophic forgetting. Specifically, our contributions are: (i) a dual memory architecture emulating the complementary learning systems (hippocampus and the neocortex) in the human brain, (ii) memory consolidation via generative replay of past experiences, (iii) demonstrating advantages of generative replay and dual memories via experiments, and (iv) improved performance retention on challenging tasks even for low capacity models. Our architecture displays many characteristics of the mammalian memory and provides insights on the connection between sleep and learning.
中文速览
灾难性遗忘（catastrophic forgetting）是神经网络在依次学习新任务时迅速丢失旧任务知识的顽固问题，根本原因在于顺序训练样本违反了梯度学习所需的独立同分布假设。受人类大脑互补学习系统（complementary learning systems）的启发，作者提出了一种双记忆深度生成架构：用一个小型"短期记忆"模块（类比海马体）快速吸收新任务，再用一个大型"长期记忆"模块（类比新皮层）通过生成式回放（generative replay）将知识逐步整合，两者在类似"睡眠"的阶段完成信息交接与巩固。在多个连续图像分类基准上，该架构在准确率和后向迁移指标上均优于正则化类与简单回放类基线方法，且在低容量模型上也能保持良好性能。这项工作不仅为持续学习提供了一条兼顾效率与记忆保留的可行路径，还为理解睡眠与学习之间的神经科学关联提供了计算层面的佐证。
原文 arXiv:1710.10368;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1710.10368v2