# Task-Free Continual Learning

## TL;DR

This paper introduces an online continual learning system that adapts to streaming data with changing distributions, removing the need for task boundaries, and demonstrates its effectiveness in face recognition and robot collision avoidance.

## Contribution

It extends Memory Aware Synapses to an online setting with protocols for importance weight updates, enabling task-free continual learning in practical scenarios.

## Key findings

- Effective in face recognition from soap series data
- Successful robot collision avoidance learning
- Demonstrates viability of task-free continual learning

## Abstract

Methods proposed in the literature towards continual deep learning typically operate in a task-based sequential learning setup. A sequence of tasks is learned, one at a time, with all data of current task available but not of previous or future tasks. Task boundaries and identities are known at all times. This setup, however, is rarely encountered in practical applications. Therefore we investigate how to transform continual learning to an online setup. We develop a system that keeps on learning over time in a streaming fashion, with data distributions gradually changing and without the notion of separate tasks. To this end, we build on the work on Memory Aware Synapses, and show how this method can be made online by providing a protocol to decide i) when to update the importance weights, ii) which data to use to update them, and iii) how to accumulate the importance weights at each update step. Experimental results show the validity of the approach in the context of two applications: (self-)supervised learning of a face recognition model by watching soap series and learning a robot to avoid collisions.