English   español  
Por favor, use este identificador para citar o enlazar a este item: http://hdl.handle.net/10261/143358
Compartir / Impacto:
Estadísticas
Add this article to your Mendeley library MendeleyBASE
Citado 0 veces en Web of Knowledge®  |  Ver citas en Google académico
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL
Exportar otros formatos: Exportar EndNote (RIS)Exportar EndNote (RIS)Exportar EndNote (RIS)
Título : Benchmarking Spike-Based Visual Recognition: A Dataset and Evaluation.
Autor : Liu, Qian; Pineda-García, Garibaldi; Stromatias, Evangelos; Serrano-Gotarredona, Teresa ; Furber, Steve B.
Palabras clave : Benchmarking
Evaluation
Neuromorphic engineering
Spiking neural networks
Vision dataset
Fecha de publicación : 2016
Editor: Frontiers Media
Citación : Frontiers in Neuroscience, 10:496. eCollection (2016)
Resumen: 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.
Versión del editor: http://dx.doi.org/10.3389/fnins.2016.00496
URI : http://hdl.handle.net/10261/143358
DOI: 10.3389/fnins.2016.00496
Aparece en las colecciones: (IMS-CNM) Artículos
Ficheros en este ítem:
Fichero Descripción Tamaño Formato  
fnins-10-00496.pdf4,09 MBAdobe PDFVista previa
Visualizar/Abrir
Mostrar el registro completo
 



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