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

01/29/2022
by   Elahe Arani, et al.
2

Humans excel at continually learning from an ever-changing environment whereas it remains a challenge for deep neural networks which exhibit catastrophic forgetting. The complementary learning system (CLS) theory suggests that the interplay between rapid instance-based learning and slow structured learning in the brain is crucial for accumulating and retaining knowledge. Here, we propose CLS-ER, a novel dual memory experience replay (ER) method which maintains short-term and long-term semantic memories that interact with the episodic memory. Our method employs an effective replay mechanism whereby new knowledge is acquired while aligning the decision boundaries with the semantic memories. CLS-ER does not utilize the task boundaries or make any assumption about the distribution of the data which makes it versatile and suited for "general continual learning". Our approach achieves state-of-the-art performance on standard benchmarks as well as more realistic general continual learning settings.

READ FULL TEXT

page 3

page 9

page 16

page 17

page 18

page 19

research
06/08/2022

SYNERgy between SYNaptic consolidation and Experience Replay for general continual learning

Continual learning (CL) in the brain is facilitated by a complex set of ...
research
10/01/2021

DualNet: Continual Learning, Fast and Slow

According to Complementary Learning Systems (CLS) theory <cit.> in neuro...
research
09/06/2022

Continual Learning: Fast and Slow

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

Continual Learning with Recursive Gradient Optimization

Learning multiple tasks sequentially without forgetting previous knowled...
research
11/03/2021

Continual Learning of Semantic Segmentation using Complementary 2D-3D Data Representations

Semantic segmentation networks are usually pre-trained and not updated d...
research
06/28/2021

Unsupervised Continual Learning via Self-Adaptive Deep Clustering Approach

Unsupervised continual learning remains a relatively uncharted territory...
research
04/20/2020

CLOPS: Continual Learning of Physiological Signals

Deep learning algorithms are known to experience destructive interferenc...

Please sign up or login with your details

Forgot password? Click here to reset