NeuroMorse: a temporally structured dataset for neuromorphic computing

Neuromorphic engineering aims to advance computing by mimicking the brain’s efficient processing, where data is encoded as asynchronous temporal events. This eliminates the need for a synchronisation clock and minimises power consumption when no data is present. However, many benchmarks for neuromor...

Full description

Saved in:
Bibliographic Details
Main Authors: Ben Walters, Yeshwanth Bethi, Taylor Kergan, Binh Nguyen, Amirali Amirsoleimani, Jason K Eshraghian, Saeed Afshar, Mostafa Rahimi Azghadi
Format: Article
Language:English
Published: IOP Publishing 2025-01-01
Series:Neuromorphic Computing and Engineering
Subjects:
Online Access:https://doi.org/10.1088/2634-4386/add36c
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849312763436859392
author Ben Walters
Yeshwanth Bethi
Taylor Kergan
Binh Nguyen
Amirali Amirsoleimani
Jason K Eshraghian
Saeed Afshar
Mostafa Rahimi Azghadi
author_facet Ben Walters
Yeshwanth Bethi
Taylor Kergan
Binh Nguyen
Amirali Amirsoleimani
Jason K Eshraghian
Saeed Afshar
Mostafa Rahimi Azghadi
author_sort Ben Walters
collection DOAJ
description Neuromorphic engineering aims to advance computing by mimicking the brain’s efficient processing, where data is encoded as asynchronous temporal events. This eliminates the need for a synchronisation clock and minimises power consumption when no data is present. However, many benchmarks for neuromorphic and spiking algorithms primarily focus on spatial features, neglecting the temporal dynamics that are inherent to most sequence-based tasks. This gap may lead to evaluations that fail to fully capture the unique strengths and characteristics of neuromorphic systems. In this paper, we present NeuroMorse, a temporally structured dataset designed for benchmarking spiking learning algorithms. NeuroMorse converts the top 50 words in the English language into temporal Morse code spike sequences. Despite using only two input spike channels for Morse dots and dashes, complex information is encoded through temporal patterns in the data. The proposed benchmark contains feature hierarchy at multiple temporal scales that test the capacity of spiking algorithms to decompose input patterns into spatial and temporal hierarchies. We demonstrate that our training set is challenging to categorise using a linear classifier and that identifying keywords in the test set is difficult using conventional methods. The NeuroMorse dataset is available at https://doi.org/10.5281/zenodo.12702379 , with our accompanying code at https://github.com/jc427648/NeuroMorse .
format Article
id doaj-art-e06e0f165ece47cd94029000e7767e17
institution Kabale University
issn 2634-4386
language English
publishDate 2025-01-01
publisher IOP Publishing
record_format Article
series Neuromorphic Computing and Engineering
spelling doaj-art-e06e0f165ece47cd94029000e7767e172025-08-20T03:52:57ZengIOP PublishingNeuromorphic Computing and Engineering2634-43862025-01-015202700110.1088/2634-4386/add36cNeuroMorse: a temporally structured dataset for neuromorphic computingBen Walters0https://orcid.org/0000-0001-5464-8468Yeshwanth Bethi1https://orcid.org/0000-0002-0713-0903Taylor Kergan2https://orcid.org/0009-0004-6277-8018Binh Nguyen3Amirali Amirsoleimani4Jason K Eshraghian5https://orcid.org/0000-0002-5832-4054Saeed Afshar6Mostafa Rahimi Azghadi7https://orcid.org/0000-0001-7975-3985College of Science and Engineering, James Cook University , Townsville, AustraliaInternational Centre for Neuromorphic Systems, Western Sydney University , Sydney, AustraliaDepartment of Electrical and Computer Engineering, University of California , Santa Cruz, The United States of AmericaDepartment of Electrical and Computer Engineering, University of California , Santa Cruz, The United States of AmericaDepartment of Electrical Engineering and Computer Science, York University , Toronto, CanadaDepartment of Electrical and Computer Engineering, University of California , Santa Cruz, The United States of AmericaInternational Centre for Neuromorphic Systems, Western Sydney University , Sydney, AustraliaCollege of Science and Engineering, James Cook University , Townsville, AustraliaNeuromorphic engineering aims to advance computing by mimicking the brain’s efficient processing, where data is encoded as asynchronous temporal events. This eliminates the need for a synchronisation clock and minimises power consumption when no data is present. However, many benchmarks for neuromorphic and spiking algorithms primarily focus on spatial features, neglecting the temporal dynamics that are inherent to most sequence-based tasks. This gap may lead to evaluations that fail to fully capture the unique strengths and characteristics of neuromorphic systems. In this paper, we present NeuroMorse, a temporally structured dataset designed for benchmarking spiking learning algorithms. NeuroMorse converts the top 50 words in the English language into temporal Morse code spike sequences. Despite using only two input spike channels for Morse dots and dashes, complex information is encoded through temporal patterns in the data. The proposed benchmark contains feature hierarchy at multiple temporal scales that test the capacity of spiking algorithms to decompose input patterns into spatial and temporal hierarchies. We demonstrate that our training set is challenging to categorise using a linear classifier and that identifying keywords in the test set is difficult using conventional methods. The NeuroMorse dataset is available at https://doi.org/10.5281/zenodo.12702379 , with our accompanying code at https://github.com/jc427648/NeuroMorse .https://doi.org/10.1088/2634-4386/add36cneuromorphic computingbenchmarksspiking neural networks
spellingShingle Ben Walters
Yeshwanth Bethi
Taylor Kergan
Binh Nguyen
Amirali Amirsoleimani
Jason K Eshraghian
Saeed Afshar
Mostafa Rahimi Azghadi
NeuroMorse: a temporally structured dataset for neuromorphic computing
Neuromorphic Computing and Engineering
neuromorphic computing
benchmarks
spiking neural networks
title NeuroMorse: a temporally structured dataset for neuromorphic computing
title_full NeuroMorse: a temporally structured dataset for neuromorphic computing
title_fullStr NeuroMorse: a temporally structured dataset for neuromorphic computing
title_full_unstemmed NeuroMorse: a temporally structured dataset for neuromorphic computing
title_short NeuroMorse: a temporally structured dataset for neuromorphic computing
title_sort neuromorse a temporally structured dataset for neuromorphic computing
topic neuromorphic computing
benchmarks
spiking neural networks
url https://doi.org/10.1088/2634-4386/add36c
work_keys_str_mv AT benwalters neuromorseatemporallystructureddatasetforneuromorphiccomputing
AT yeshwanthbethi neuromorseatemporallystructureddatasetforneuromorphiccomputing
AT taylorkergan neuromorseatemporallystructureddatasetforneuromorphiccomputing
AT binhnguyen neuromorseatemporallystructureddatasetforneuromorphiccomputing
AT amiraliamirsoleimani neuromorseatemporallystructureddatasetforneuromorphiccomputing
AT jasonkeshraghian neuromorseatemporallystructureddatasetforneuromorphiccomputing
AT saeedafshar neuromorseatemporallystructureddatasetforneuromorphiccomputing
AT mostafarahimiazghadi neuromorseatemporallystructureddatasetforneuromorphiccomputing