DeepAI
Log In Sign Up

DualNet: Continual Learning, Fast and Slow

10/01/2021
by   Quang Pham, et al.
0

According to Complementary Learning Systems (CLS) theory <cit.> in neuroscience, humans do effective continual learning through two complementary systems: a fast learning system centered on the hippocampus for rapid learning of the specifics and individual experiences, and a slow learning system located in the neocortex for the gradual acquisition of structured knowledge about the environment. Motivated by this theory, we propose a novel continual learning framework named "DualNet", which comprises a fast learning system for supervised learning of pattern-separated representation from specific tasks and a slow learning system for unsupervised representation learning of task-agnostic general representation via a Self-Supervised Learning (SSL) technique. The two fast and slow learning systems are complementary and work seamlessly in a holistic continual learning framework. Our extensive experiments on two challenging continual learning benchmarks of CORE50 and miniImageNet show that DualNet outperforms state-of-the-art continual learning methods by a large margin. We further conduct ablation studies of different SSL objectives to validate DualNet's efficacy, robustness, and scalability. Code will be made available upon acceptance.

READ FULL TEXT
09/06/2022

Continual Learning: Fast and Slow

According to the Complementary Learning Systems (CLS) theory <cit.> in n...
01/29/2022

Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning System

Humans excel at continually learning from an ever-changing environment w...
04/19/2021

Few-shot Continual Learning: a Brain-inspired Approach

It is an important yet challenging setting to continually learn new task...
09/11/2022

Continual Learning for Pose-Agnostic Object Recognition in 3D Point Clouds

Continual Learning aims to learn multiple incoming new tasks continually...
06/01/2022

Label-Efficient Online Continual Object Detection in Streaming Video

To thrive in evolving environments, humans are capable of continual acqu...
10/10/2022

A Simple Baseline that Questions the Use of Pretrained-Models in Continual Learning

With the success of pretraining techniques in representation learning, a...
05/07/2019

A Complementary Learning Systems Approach to Temporal Difference Learning

Complementary Learning Systems (CLS) theory suggests that the brain uses...