# Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learning

## TL;DR

This paper introduces Dynamic Generative Memory, a synaptic plasticity-based framework for continual learning that uses generative adversarial networks and neural masking to retain old knowledge and expand capacity dynamically.

## Contribution

It presents a novel framework combining generative models, neural masking, and dynamic expansion to improve continual learning performance and scalability.

## Key findings

- Effective retention of old knowledge in continual learning tasks
- Dynamic capacity expansion improves scalability
- Neural masking enhances model flexibility

## Abstract

Models trained in the context of continual learning (CL) should be able to learn from a stream of data over an undefined period of time. The main challenges herein are: 1) maintaining old knowledge while simultaneously benefiting from it when learning new tasks, and 2) guaranteeing model scalability with a growing amount of data to learn from. In order to tackle these challenges, we introduce Dynamic Generative Memory (DGM) - a synaptic plasticity driven framework for continual learning. DGM relies on conditional generative adversarial networks with learnable connection plasticity realized with neural masking. Specifically, we evaluate two variants of neural masking: applied to (i) layer activations and (ii) to connection weights directly. Furthermore, we propose a dynamic network expansion mechanism that ensures sufficient model capacity to accommodate for continually incoming tasks. The amount of added capacity is determined dynamically from the learned binary mask. We evaluate DGM in the continual class-incremental setup on visual classification tasks.