An unsupervised neuromorphic clustering algorithm

Diamand, Alan, Schmuker, Michael and Nowotny, Thomas (2019) An unsupervised neuromorphic clustering algorithm. Biological Cybernetics. ISSN 0340-1200

[img] PDF - Published Version
Available under License Creative Commons Attribution.

Download (3MB)

Abstract

Brains perform complex tasks using a fraction of the power that would be required to do the same on a conventional computer. New neuromorphic hardware systems are now becoming widely available that are intended to emulate the more power efficient, highly parallel operation of brains. However, to use these systems in applications, we need “neuromorphic algorithms” that can run on them. Here we develop a spiking neural network model for neuromorphic hardware that uses spike timing-dependent plasticity and lateral inhibition to perform unsupervised clustering. With this model, time-invariant, rate-coded datasets can be mapped into a feature space with a specified resolution, i.e., number of clusters, using exclusively neuromorphic hardware. We developed and tested implementations on the SpiNNaker neuromorphic system and on GPUs using the GeNN framework. We show that our neuromorphic clustering algorithm achieves results comparable to those of conventional clustering algorithms such as self-organizing maps, neural gas or k-means clustering. We then combine it with a previously reported supervised neuromorphic classifier network to demonstrate its practical use as a neuromorphic preprocessing module.

Item Type: Article
Keywords: Neuromorphic hardware; Self-organizing map; Data clustering; Unsupervised learning; Spiking neural networks; Classification
Schools and Departments: School of Engineering and Informatics > Informatics
Research Centres and Groups: Centre for Computational Neuroscience and Robotics
Evolutionary and Adaptive Systems Research Group
Subjects: Q Science
Q Science > Q Science (General) > Q0300 Cybernetics > Q0325 Self-organizing systems. Conscious automata
Q Science > Q Science (General) > Q0300 Cybernetics > Q0325 Self-organizing systems. Conscious automata > Q0334 Artificial intelligence
Q Science > Q Science (General) > Q0300 Cybernetics > Q0325 Self-organizing systems. Conscious automata > Q0334 Artificial intelligence > Q0337.5 Pattern recognition systems
Q Science > QA Mathematics > QA0075 Electronic computers. Computer science
Depositing User: Thomas Nowotny
Date Deposited: 05 Apr 2019 10:36
Last Modified: 05 Apr 2019 10:36
URI: http://srodev.sussex.ac.uk/id/eprint/83043

View download statistics for this item

📧 Request an update
Project NameSussex Project NumberFunderFunder Ref
Biomachinelearning: Bio-inspired Machine Learning for Chemical Sensing (fellow: Michael Schmuker)G1382EUROPEAN UNIONPIEF-GA-2012-331892
Human Brain Project: Neuromorphic Implementations of Multivariate Classification Inspired by the Olfactory SystemG1359EUROPEAN UNION604102 HBP NEUROCLASSIOS
Human Brain Project Specific Grant Agreement 1 - HBP SGA1G1972EUROPEAN UNION72027
Human Brian Project Specific Grant Agreement 2G2410EUROPEAN UNION785907
Odor-background segregation and source localization using fast olfactory processingG1652HUMAN FRONTIER SCIENCE PROGRAM (HFSP)RGP0053/2015