Neuromimetic metaplasticity for adaptive continual learning

TL;DR

This paper introduces a neuromimetic metaplasticity model inspired by human memory that enables deep neural networks to learn continuously without catastrophic forgetting, while also resisting data poisoning attacks.

Contribution

The proposed model uniquely combines synapse types with varying flexibility to prevent forgetting and enhance robustness without extra training or structural changes.

Findings

Successfully learned continuous information streams despite input changes

Achieved a balance between memory capacity and performance

Demonstrated robustness against data poisoning attacks

Abstract

Conventional intelligent systems based on deep neural network (DNN) models encounter challenges in achieving human-like continual learning due to catastrophic forgetting. Here, we propose a metaplasticity model inspired by human working memory, enabling DNNs to perform catastrophic forgetting-free continual learning without any pre- or post-processing. A key aspect of our approach involves implementing distinct types of synapses from stable to flexible, and randomly intermixing them to train synaptic connections with different degrees of flexibility. This strategy allowed the network to successfully learn a continuous stream of information, even under unexpected changes in input length. The model achieved a balanced tradeoff between memory capacity and performance without requiring additional training or structural modifications, dynamically allocating memory resources to retain both old and new information. Furthermore, the model demonstrated robustness against data poisoning attacks by selectively filtering out erroneous memories, leveraging the Hebb repetition effect to reinforce the retention of significant data.