Dendritic Self-Organizing Maps for Continual Learning

TL;DR

This paper introduces Dendritic-Self-Organizing Maps (DendSOM), a biologically inspired algorithm that enhances continual learning by reducing catastrophic forgetting in neural networks.

Contribution

The paper presents DendSOM, a novel SOM-based algorithm that models input space regions and employs hit matrices for label association, improving continual learning performance.

Findings

DendSOM outperforms classical SOMs and state-of-the-art continual learning algorithms.

DendSOM effectively mitigates catastrophic forgetting in benchmark datasets.

DendSOM uses unsupervised feature extraction without label-based weight updates.

Abstract

Current deep learning architectures show remarkable performance when trained in large-scale, controlled datasets. However, the predictive ability of these architectures significantly decreases when learning new classes incrementally. This is due to their inclination to forget the knowledge acquired from previously seen data, a phenomenon termed catastrophic-forgetting. On the other hand, Self-Organizing Maps (SOMs) can model the input space utilizing constrained k-means and thus maintain past knowledge. Here, we propose a novel algorithm inspired by biological neurons, termed Dendritic-Self-Organizing Map (DendSOM). DendSOM consists of a single layer of SOMs, which extract patterns from specific regions of the input space accompanied by a set of hit matrices, one per SOM, which estimate the association between units and labels. The best-matching unit of an input pattern is selected using the maximum cosine similarity rule, while the point-wise mutual information is employed for class inference. DendSOM performs unsupervised feature extraction as it does not use labels for targeted updating of the weights. It outperforms classical SOMs and several state-of-the-art continual learning algorithms on benchmark datasets, such as the Split-MNIST and Split-CIFAR-10. We propose that the incorporation of neuronal properties in SOMs may help remedy catastrophic forgetting.