DynMat, a network that can learn after learning

TL;DR

DynMat is a neural network architecture inspired by brain systems, capable of online, accumulative learning without catastrophic interference, enabling continuous learning similar to human cognition.

Contribution

The paper introduces DynMat, a novel neural network that learns continuously without catastrophic interference, inspired by the brain's complementary learning systems.

Findings

DynMat learns new classes without forgetting old ones.

It operates effectively without offline training.

Demonstrates online, accumulative learning capabilities.

Abstract

To survive in the dynamically-evolving world, we accumulate knowledge and improve our skills based on experience. In the process, gaining new knowledge does not disrupt our vigilance to external stimuli. In other words, our learning process is 'accumulative' and 'online' without interruption. However, despite the recent success, artificial neural networks (ANNs) must be trained offline, and they suffer catastrophic interference between old and new learning, indicating that ANNs' conventional learning algorithms may not be suitable for building intelligent agents comparable to our brain. In this study, we propose a novel neural network architecture (DynMat) consisting of dual learning systems, inspired by the complementary learning system (CLS) theory suggesting that the brain relies on short- and long-term learning systems to learn continuously. Our experiments show that 1) DynMat can learn a new class without catastrophic interference and 2) it does not strictly require offline training.