Rehearsal-based Continual Learning (CL) has been intensely investigated in
Deep Neural Networks (DNNs). However, its application in Spiking Neural
Networks (SNNs) has not been explored in depth. In this paper we introduce the
first memory-efficient implementation of Latent Replay (LR)-based CL for SNNs,
designed to seamlessly integrate with resource-constrained devices. LRs combine
new samples with latent representations of previously learned data, to mitigate
forgetting. Experiments on the Heidelberg SHD dataset with Sample and
Class-Incremental tasks reach a Top-1 accuracy of 92.5% and 92%, respectively,
without forgetting the previously learned information. Furthermore, we minimize
the LRs' requirements by applying a time-domain compression, reducing by two
orders of magnitude their memory requirement, with respect to a naive rehearsal
setup, with a maximum accuracy drop of 4%. On a Multi-Class-Incremental task,
our SNN learns 10 new classes from an initial set of 10, reaching a Top-1
accuracy of 78.4% on the full test set.

基于回顾的持续学习在深度神经网络中被广泛研究，然而在脉冲神经网络中的应用尚未深入探索。本文介绍了第一种用于脉冲神经网络的内存高效实现的潜在重放（LR）- 基于回顾持续学习，旨在与资源受限设备无缝集成。实验结果表明，在 Heidelberg SHD 数据集上进行的示例和类增量任务中，Top-1 准确率分别达到 92.5％和 92％，而不会忘记先前学到的信息。此外，通过应用时间域压缩，我们将 LR 的存储要求减少了两个数量级，并且与简单的回顾设置相比，最大准确率下降仅为 4％。在多类增量任务中，我们的脉冲神经网络从初始的 10 个类别学习了 10 个新类别，最终在完整测试集上达到了 78.4％的 Top-1 准确率。

基于压缩潜在重放的轻量级脉冲神经网络的持续学习

Compressed Latent Replays for Lightweight Continual Learning on Spiking  Neural Networks

Recently, deep residual networks have been successfully applied in many
computer vision and natural language processing tasks, pushing the
state-of-the-art performance with deeper and wider architectures. In this work,
we interpret deep residual networks as ordinary differential equations (ODEs),
which have long been studied in mathematics and physics with rich theoretical
and empirical success. From this interpretation, we develop a theoretical
framework on stability and reversibility of deep neural networks, and derive
three reversible neural network architectures that can go arbitrarily deep in
theory. The reversibility property allows a memory-efficient implementation,
which does not need to store the activations for most hidden layers. Together
with the stability of our architectures, this enables training deeper networks
using only modest computational resources. We provide both theoretical analyses
and empirical results. Experimental results demonstrate the efficacy of our
architectures against several strong baselines on CIFAR-10, CIFAR-100 and
STL-10 with superior or on-par state-of-the-art performance. Furthermore, we
show our architectures yield superior results when trained using fewer training
data.

本研究将深度残差网络解释为普通微分方程，并由此开发出一种稳定和可逆的深度神经网络理论框架，以及提出了三种可任意加深的可逆神经网络架构，实现了对深度网络的记忆高效实现，并且通过实验证明了本文方法在 CIFAR-10，CIFAR-100 和 STL-10 等数据集上取得了明显的优于现有强基准的性能表现，并且能够通过使用更少的训练数据来训练神经网络。