Improving Performance in Continual Learning Tasks using Bio-Inspired Architectures

TL;DR

This paper introduces a biologically inspired neural network architecture that enables online continual learning without stochastic gradient descent, outperforming memory-constrained methods and matching state-of-the-art replay-based approaches.

Contribution

The authors develop a lightweight, biologically inspired architecture with synaptic plasticity and neuromodulation for online continual learning, avoiding the need for stochastic gradient descent.

Findings

Superior performance on Split-MNIST, Split-CIFAR-10, and Split-CIFAR-100 datasets.

Improves accuracy of other continual learning algorithms by integrating biological principles.

Matches state-of-the-art replay-based methods without requiring memory buffers.

Abstract

The ability to learn continuously from an incoming data stream without catastrophic forgetting is critical to designing intelligent systems. Many approaches to continual learning rely on stochastic gradient descent and its variants that employ global error updates, and hence need to adopt strategies such as memory buffers or replay to circumvent its stability, greed, and short-term memory limitations. To address this limitation, we have developed a biologically inspired lightweight neural network architecture that incorporates synaptic plasticity mechanisms and neuromodulation and hence learns through local error signals to enable online continual learning without stochastic gradient descent. Our approach leads to superior online continual learning performance on Split-MNIST, Split-CIFAR-10, and Split-CIFAR-100 datasets compared to other memory-constrained learning approaches and matches that of the state-of-the-art memory-intensive replay-based approaches. We further demonstrate the effectiveness of our approach by integrating key design concepts into other backpropagation-based continual learning algorithms, significantly improving their accuracy. Our results provide compelling evidence for the importance of incorporating biological principles into machine learning models and offer insights into how we can leverage them to design more efficient and robust systems for online continual learning.