Continual learning (CL) in the brain is facilitated by a complex set of
mechanisms. This includes the interplay of multiple memory systems for
consolidating information as posited by the complementary learning systems
(CLS) theory and synaptic consolidation for protecting the acquired knowledge
from erasure. Thus, we propose a general CL method that creates a synergy
between SYNaptic consolidation and dual memory Experience Replay (SYNERgy). Our
method maintains a semantic memory that accumulates and consolidates
information across the tasks and interacts with the episodic memory for
effective replay. It further employs synaptic consolidation by tracking the
importance of parameters during the training trajectory and anchoring them to
the consolidated parameters in the semantic memory. To the best of our
knowledge, our study is the first to employ dual memory experience replay in
conjunction with synaptic consolidation that is suitable for general CL whereby
the network does not utilize task boundaries or task labels during training or
inference. Our evaluation on various challenging CL scenarios and
characteristics analyses demonstrate the efficacy of incorporating both
synaptic consolidation and CLS theory in enabling effective CL in DNNs.

该研究提出了一种基于 SYNaptic consolidation 和 dual memory experience replay 的通用 CL 方法，通过维护语义记忆来实现跨任务信息的累积和巩固，并结合突触巩固以实现高效的连续学习，不需要使用任务标签。

突触巩固和体验回放在通用持续学习中的协同作用

SYNERgy between SYNaptic consolidation and Experience Replay for general continual learning

A central challenge faced by memory systems is the robust retrieval of a
stored pattern in the presence of interference due to other stored patterns and
noise. A theoretically well-founded solution to robust retrieval is given by
attractor dynamics, which iteratively clean up patterns during recall. However,
incorporating attractor dynamics into modern deep learning systems poses
difficulties: attractor basins are characterised by vanishing gradients, which
are known to make training neural networks difficult. In this work, we avoid
the vanishing gradient problem by training a generative distributed memory
without simulating the attractor dynamics. Based on the idea of memory writing
as inference, as proposed in the Kanerva Machine, we show that a
likelihood-based Lyapunov function emerges from maximising the variational
lower-bound of a generative memory. Experiments shows it converges to correct
patterns upon iterative retrieval and achieves competitive performance as both
a memory model and a generative model.

本研究展示了一个基于 Kanerva 机器提出的记忆写入即推理的思想，通过训练一个生成式分布式记忆，最大化其变分下界导出一个儒雅彼诺夫函数。实验结果表明，在迭代读取中收敛到正确的模式，并且在记忆模型和生成模型方面都具有有竞争力的性能。