Benchmarking Spike-Based Visual Recognition: A Dataset and Evaluation

Today, increasing attention is being paid to research into spike-based neural computation both to gain a better understanding of the brain and to explore biologically-inspired computation. Within this field, the primate visual pathway and its hierarchical organization have been extensively studied....

Descripción completa

Detalles Bibliográficos
Autores: Liu, Qian, Pineda García, Garibaldi, Stromatias, Evangelos, Serrano Gotarredona, María Teresa, Furber, Steve B.
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2016
País:España
Institución:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/73758
Acceso en línea:https://hdl.handle.net/11441/73758
https://doi.org/10.3389/fnins.2016.00496
Access Level:acceso abierto
Palabra clave:Benchmarking
Evaluation
Neuromorphic engineering
Spiking neural networks
Vision dataset
id ES_7e003978faa3fd05f16c44198ffb3fc0
oai_identifier_str oai:idus.us.es:11441/73758
network_acronym_str ES
network_name_str España
repository_id_str
spelling Benchmarking Spike-Based Visual Recognition: A Dataset and EvaluationLiu, QianPineda García, GaribaldiStromatias, EvangelosSerrano Gotarredona, María TeresaFurber, Steve B.BenchmarkingEvaluationNeuromorphic engineeringSpiking neural networksVision datasetToday, increasing attention is being paid to research into spike-based neural computation both to gain a better understanding of the brain and to explore biologically-inspired computation. Within this field, the primate visual pathway and its hierarchical organization have been extensively studied. Spiking Neural Networks (SNNs), inspired by the understanding of observed biological structure and function, have been successfully applied to visual recognition and classification tasks. In addition, implementations on neuromorphic hardware have enabled large-scale networks to run in (or even faster than) real time, making spike-based neural vision processing accessible on mobile robots. Neuromorphic sensors such as silicon retinas are able to feed such mobile systems with real-time visual stimuli. A new set of vision benchmarks for spike-based neural processing are now needed to measure progress quantitatively within this rapidly advancing field. We propose that a large dataset of spike-based visual stimuli is needed to provide meaningful comparisons between different systems, and a corresponding evaluation methodology is also required to measure the performance of SNN models and their hardware implementations. In this paper we first propose an initial NE (Neuromorphic Engineering) dataset based on standard computer vision benchmarksand that uses digits from the MNIST database. This dataset is compatible with the state of current research on spike-based image recognition. The corresponding spike trains are produced using a range of techniques: rate-based Poisson spike generation, rank order encoding, and recorded output from a silicon retina with both flashing and oscillating input stimuli. In addition, a complementary evaluation methodology is presented to assess both model-level and hardware-level performance. Finally, we demonstrate the use of the dataset and the evaluation methodology using two SNN models to validate the performance of the models and their hardware implementations. With this dataset we hope to (1) promote meaningful comparison between algorithms in the field of neural computation, (2) allow comparison with conventional image recognition methods, (3) provide an assessment of the state of the art in spike-based visual recognition, and (4) help researchers identify future directions and advance the field.Engineering and Physical Sciences Research Council EP/4015740/1European Union 320689, FP7-604102Frontiers MediaArquitectura y Tecnología de ComputadoresEngineering and Physical Sciences Research Council (UK)European Union (UE)2016info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttps://hdl.handle.net/11441/73758https://doi.org/10.3389/fnins.2016.00496reponame:idUS. Depósito de Investigación de la Universidad de Sevillainstname:Universidad de Sevilla (US)InglésFrontiers in Neuroscience, 10, 496-.EP/4015740/1320689FP7-604102http://dx.doi.org/10.3389/fnins.2016.00496info:eu-repo/semantics/openAccessoai:idus.us.es:11441/737582026-06-17T12:51:07Z
dc.title.none.fl_str_mv Benchmarking Spike-Based Visual Recognition: A Dataset and Evaluation
title Benchmarking Spike-Based Visual Recognition: A Dataset and Evaluation
spellingShingle Benchmarking Spike-Based Visual Recognition: A Dataset and Evaluation
Liu, Qian
Benchmarking
Evaluation
Neuromorphic engineering
Spiking neural networks
Vision dataset
title_short Benchmarking Spike-Based Visual Recognition: A Dataset and Evaluation
title_full Benchmarking Spike-Based Visual Recognition: A Dataset and Evaluation
title_fullStr Benchmarking Spike-Based Visual Recognition: A Dataset and Evaluation
title_full_unstemmed Benchmarking Spike-Based Visual Recognition: A Dataset and Evaluation
title_sort Benchmarking Spike-Based Visual Recognition: A Dataset and Evaluation
dc.creator.none.fl_str_mv Liu, Qian
Pineda García, Garibaldi
Stromatias, Evangelos
Serrano Gotarredona, María Teresa
Furber, Steve B.
author Liu, Qian
author_facet Liu, Qian
Pineda García, Garibaldi
Stromatias, Evangelos
Serrano Gotarredona, María Teresa
Furber, Steve B.
author_role author
author2 Pineda García, Garibaldi
Stromatias, Evangelos
Serrano Gotarredona, María Teresa
Furber, Steve B.
author2_role author
author
author
author
dc.contributor.none.fl_str_mv Arquitectura y Tecnología de Computadores
Engineering and Physical Sciences Research Council (UK)
European Union (UE)
dc.subject.none.fl_str_mv Benchmarking
Evaluation
Neuromorphic engineering
Spiking neural networks
Vision dataset
topic Benchmarking
Evaluation
Neuromorphic engineering
Spiking neural networks
Vision dataset
description Today, increasing attention is being paid to research into spike-based neural computation both to gain a better understanding of the brain and to explore biologically-inspired computation. Within this field, the primate visual pathway and its hierarchical organization have been extensively studied. Spiking Neural Networks (SNNs), inspired by the understanding of observed biological structure and function, have been successfully applied to visual recognition and classification tasks. In addition, implementations on neuromorphic hardware have enabled large-scale networks to run in (or even faster than) real time, making spike-based neural vision processing accessible on mobile robots. Neuromorphic sensors such as silicon retinas are able to feed such mobile systems with real-time visual stimuli. A new set of vision benchmarks for spike-based neural processing are now needed to measure progress quantitatively within this rapidly advancing field. We propose that a large dataset of spike-based visual stimuli is needed to provide meaningful comparisons between different systems, and a corresponding evaluation methodology is also required to measure the performance of SNN models and their hardware implementations. In this paper we first propose an initial NE (Neuromorphic Engineering) dataset based on standard computer vision benchmarksand that uses digits from the MNIST database. This dataset is compatible with the state of current research on spike-based image recognition. The corresponding spike trains are produced using a range of techniques: rate-based Poisson spike generation, rank order encoding, and recorded output from a silicon retina with both flashing and oscillating input stimuli. In addition, a complementary evaluation methodology is presented to assess both model-level and hardware-level performance. Finally, we demonstrate the use of the dataset and the evaluation methodology using two SNN models to validate the performance of the models and their hardware implementations. With this dataset we hope to (1) promote meaningful comparison between algorithms in the field of neural computation, (2) allow comparison with conventional image recognition methods, (3) provide an assessment of the state of the art in spike-based visual recognition, and (4) help researchers identify future directions and advance the field.
publishDate 2016
dc.date.none.fl_str_mv 2016
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/11441/73758
https://doi.org/10.3389/fnins.2016.00496
url https://hdl.handle.net/11441/73758
https://doi.org/10.3389/fnins.2016.00496
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Frontiers in Neuroscience, 10, 496-.
EP/4015740/1
320689
FP7-604102
http://dx.doi.org/10.3389/fnins.2016.00496
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Frontiers Media
publisher.none.fl_str_mv Frontiers Media
dc.source.none.fl_str_mv reponame:idUS. Depósito de Investigación de la Universidad de Sevilla
instname:Universidad de Sevilla (US)
instname_str Universidad de Sevilla (US)
reponame_str idUS. Depósito de Investigación de la Universidad de Sevilla
collection idUS. Depósito de Investigación de la Universidad de Sevilla
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869411705199525888
score 15,301603

Similares en LA Referencia