Por favor, use este identificador para citar o enlazar a este item:
http://hdl.handle.net/10261/153732
COMPARTIR / EXPORTAR:
SHARE CORE BASE | |
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE | |
Título: | An Event-Driven Classifier for Spiking Neural Networks Fed with Synthetic or Dynamic Vision Sensor Data |
Autor: | Stromatias, Evangelos CSIC; Soto, Miguel CSIC; Serrano-Gotarredona, Teresa CSIC ORCID ; Linares-Barranco, Bernabé CSIC ORCID | Palabras clave: | Spiking neural networks Supervised learning Event driven processing DVS sensors Convolutional neural networks Fully connected neural networks, Neuromorphic |
Fecha de publicación: | 2017 | Editor: | Frontiers Media | Citación: | Frontiers in Neuroscience, 11 : 350 (2017) | Resumen: | 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. | Versión del editor: | htpp://dx.doi.org/10.3389/fnins.2017.00350 | URI: | http://hdl.handle.net/10261/153732 | DOI: | 10.3389/fnins.2017.00350 |
Aparece en las colecciones: | (IMSE-CNM) Artículos |
Ficheros en este ítem:
Fichero | Descripción | Tamaño | Formato | |
---|---|---|---|---|
Linares Barranco.pdf | 5,22 MB | Adobe PDF | Visualizar/Abrir |
CORE Recommender
PubMed Central
Citations
14
checked on 10-may-2024
SCOPUSTM
Citations
86
checked on 09-may-2024
WEB OF SCIENCETM
Citations
70
checked on 29-feb-2024
Page view(s)
594
checked on 13-may-2024
Download(s)
450
checked on 13-may-2024
Google ScholarTM
Check
Altmetric
Altmetric
Artículos relacionados:
NOTA: Los ítems de Digital.CSIC están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.