dc.creator | Stromatias, Evangelos | es |
dc.creator | Soto, Miguel | es |
dc.creator | Serrano Gotarredona, María Teresa | es |
dc.creator | Linares Barranco, Bernabé | es |
dc.date.accessioned | 2018-01-31T12:31:08Z | |
dc.date.available | 2018-01-31T12:31:08Z | |
dc.date.issued | 2017 | |
dc.identifier.citation | Stromatias, E., Soto, M., Serrano Gotarredona, M.T. y Linares Barranco, B. (2017). An event-based classifier for Dynamic Vision Sensor and synthetic data. Frontiers in Neuroscience, 11 (artículo 360) | |
dc.identifier.issn | 1662-4548 | es |
dc.identifier.issn | 1662-453X | es |
dc.identifier.uri | https://hdl.handle.net/11441/69815 | |
dc.description.abstract | This paper introduces a novel methodology for training an event-driven classifier within
a Spiking Neural Network (SNN) System capable of yielding good classification results
when using both synthetic input data and real data captured from Dynamic Vision Sensor
(DVS) chips. The proposed supervised method uses the spiking activity provided by an
arbitrary topology of prior SNN layers to build histograms and train the classifier in the
frame domain using the stochastic gradient descent algorithm. In addition, this approach
can cope with leaky integrate-and-fire neuron models within the SNN, a desirable feature
for real-world SNN applications, where neural activation must fade away after some
time in the absence of inputs. Consequently, this way of building histograms captures
the dynamics of spikes immediately before the classifier. We tested our method on
the MNIST data set using different synthetic encodings and real DVS sensory data
sets such as N-MNIST, MNIST-DVS, and Poker-DVS using the same network topology
and feature maps. We demonstrate the effectiveness of our approach by achieving
the highest classification accuracy reported on the N-MNIST (97.77%) and Poker-DVS
(100%) real DVS data sets to date with a spiking convolutional network. Moreover, by
using the proposed method we were able to retrain the output layer of a previously
reported spiking neural network and increase its performance by 2%, suggesting that
the proposed classifier can be used as the output layer in works where features are
extracted using unsupervised spike-based learningmethods. In addition, we also analyze
SNN performance figures such as total event activity and network latencies, which
are relevant for eventual hardware implementations. In summary, the paper aggregates
unsupervised-trained SNNs with a supervised-trained SNN classifier, combining and
applying them to heterogeneous sets of benchmarks, both synthetic and from real DVS
chips. | es |
dc.description.sponsorship | Samsung Advanced Institute of Technology EU H2020 644096 | es |
dc.description.sponsorship | Samsung Advanced Institute of Technology EU H2020 687299 | es |
dc.description.sponsorship | Ministerio de Economía y Competitividad TEC2012-37868-C04-01 | es |
dc.description.sponsorship | Ministerio de Economía y Competitividad TEC2015-63884-C2-1-P | es |
dc.description.sponsorship | Junta de Andalucía TIC-6091 | es |
dc.format | application/pdf | es |
dc.language.iso | eng | es |
dc.publisher | Frontiers Media | es |
dc.relation.ispartof | Frontiers in Neuroscience, 11 (artículo 360) | |
dc.rights | Attribution-NonCommercial-NoDerivatives 4.0 Internacional | * |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | * |
dc.subject | Spiking neural networks | es |
dc.subject | Supervised learning | es |
dc.subject | Event driven processing | es |
dc.subject | DVS sensors | es |
dc.subject | Convolutional neural networks | es |
dc.subject | Fully connected neural networks | es |
dc.subject | Neuromorphic | es |
dc.title | An event-based classifier for Dynamic Vision Sensor and synthetic data | es |
dc.type | info:eu-repo/semantics/article | es |
dcterms.identifier | https://ror.org/03yxnpp24 | |
dc.type.version | info:eu-repo/semantics/publishedVersion | es |
dc.rights.accessRights | info:eu-repo/semantics/openAccess | es |
dc.contributor.affiliation | Universidad de Sevilla. Departamento de Arquitectura y Tecnología de Computadores | es |
dc.relation.projectID | EU H2020 644096 | es |
dc.relation.projectID | EU H2020 687299 | es |
dc.relation.projectID | TEC2012-37868-C04-01 | es |
dc.relation.projectID | TEC2015-63884-C2-1-P | es |
dc.relation.projectID | TIC-6091 | es |
dc.relation.publisherversion | https://www.frontiersin.org/articles/10.3389/fnins.2017.00350/full | es |
dc.identifier.doi | 10.3389/fnins.2017.00350 | es |
dc.contributor.group | Universidad de Sevilla. TIC178: Diseño y Test de Circuitos Integrados de Señal Mixta | es |
idus.format.extent | 17 | es |
dc.journaltitle | Frontiers in Neuroscience | es |
dc.publication.volumen | 11 | es |
dc.publication.issue | artículo 360 | es |
dc.identifier.sisius | 21327174 | es |