Log In Sign Up

HyperSeed: Unsupervised Learning with Vector Symbolic Architectures

by   Evgeny Osipov, et al.

Motivated by recent innovations in biologically-inspired neuromorphic hardware, this paper presents a novel unsupervised machine learning approach named Hyperseed that leverages Vector Symbolic Architectures (VSA) for fast learning a topology preserving feature map of unlabelled data. It relies on two major capabilities of VSAs: the binding operation and computing in superposition. In this paper, we introduce the algorithmic part of Hyperseed expressed within Fourier Holographic Reduced Representations VSA model, which is specifically suited for implementation on spiking neuromorphic hardware. The two distinctive novelties of the Hyperseed algorithm are: 1) Learning from only few input data samples and 2) A learning rule based on a single vector operation. These properties are demonstrated on synthetic datasets as well as on illustrative benchmark use-cases, IRIS classification and a language identification task using n-gram statistics.


page 1

page 2

page 3

page 4


Vector Symbolic Architectures as a Computing Framework for Nanoscale Hardware

This article reviews recent progress in the development of the computing...

Unsupervised Competitive Hardware Learning Rule for Spintronic Clustering Architecture

We propose a hardware learning rule for unsupervised clustering within a...

A Scalable Approach to Modeling on Accelerated Neuromorphic Hardware

Neuromorphic systems open up opportunities to enlarge the explorative sp...

P-CRITICAL: A Reservoir Autoregulation Plasticity Rule for Neuromorphic Hardware

Backpropagation algorithms on recurrent artificial neural networks requi...

Design Space Exploration of Hardware Spiking Neurons for Embedded Artificial Intelligence

Machine learning is yielding unprecedented interest in research and indu...

Residual and Attentional Architectures for Vector-Symbols

Vector-symbolic architectures (VSAs) provide methods for computing which...

Recursive Binding for Similarity-Preserving Hypervector Representations of Sequences

Hyperdimensional computing (HDC), also known as vector symbolic architec...