Hyperseed: Unsupervised Learning with Vector Symbolic Architectures

TL;DR

Hyperseed is an unsupervised learning algorithm inspired by neuromorphic hardware and Vector Symbolic Architectures, enabling fast, topology-preserving feature learning with few-shot capabilities on synthetic and real datasets.

Contribution

It introduces Hyperseed, a novel unsupervised learning method based on VSA principles, suitable for implementation on neuromorphic hardware, with unique single-vector learning rules.

Findings

Effective on synthetic datasets and benchmark tasks.

Supports few-shot learning with a single vector operation.

Demonstrates potential for neuromorphic hardware applications.

Abstract

Motivated by recent innovations in biologically-inspired neuromorphic hardware, this article presents a novel unsupervised machine learning algorithm named Hyperseed that draws on the principles of Vector Symbolic Architectures (VSA) for fast learning of a topology preserving feature map of unlabelled data. It relies on two major operations of VSA, binding and bundling. The algorithmic part of Hyperseed is expressed within Fourier Holographic Reduced Representations model, which is specifically suited for implementation on spiking neuromorphic hardware. The two primary contributions of the Hyperseed algorithm are, few-shot learning and a learning rule based on single vector operation. These properties are empirically evaluated on synthetic datasets as well as on illustrative benchmark use-cases, IRIS classification, and a language identification task using n-gram statistics. The results of these experiments confirm the capabilities of Hyperseed and its applications in neuromorphic hardware.