English   español  
Por favor, use este identificador para citar o enlazar a este item: http://hdl.handle.net/10261/153732
logo share SHARE logo core CORE   Add this article to your Mendeley library MendeleyBASE

Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL
Exportar a otros formatos:

An Event-Driven Classifier for Spiking Neural Networks Fed with Synthetic or Dynamic Vision Sensor Data

AutorStromatias, Evangelos; Soto, Miguel; Serrano-Gotarredona, Teresa ; Linares-Barranco, Bernabé
Palabras claveSpiking neural networks
Supervised learning
Event driven processing
DVS sensors
Convolutional neural networks
Fully connected neural networks,
Fecha de publicación2017
EditorFrontiers Media
CitaciónFrontiers in Neuroscience, 11 : 350 (2017)
ResumenThis 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 editorhtpp://dx.doi.org/10.3389/fnins.2017.00350
Aparece en las colecciones: (IMSE-CNM) Artículos
Ficheros en este ítem:
Fichero Descripción Tamaño Formato  
Linares Barranco.pdf5,22 MBAdobe PDFVista previa
Mostrar el registro completo

Artículos relacionados:

NOTA: Los ítems de Digital.CSIC están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.