Fast Pipeline 128x128 Pixel Spiking Convolution Core for Event-Driven Vision Processing in FPGAs
| Autor: | Yousefzadeh, Amirreza, Serrano Gotarredona, María Teresa, Linares Barranco, Bernabé |
|---|---|
| Přispěvatelé: | Universidad de Sevilla. Departamento de Arquitectura y Tecnología de Computadores, Universidad de Sevilla. TIC178: Diseño y Test de Circuitos Integrados de Señal Mixta |
| Rok vydání: | 2015 |
| Předmět: | |
| Zdroj: | idUS. Depósito de Investigación de la Universidad de Sevilla instname idUS: Depósito de Investigación de la Universidad de Sevilla Universidad de Sevilla (US) |
| Popis: | This paper describes a digital implementation of a parallel and pipelined spiking convolutional neural network (SConvNet) core for processing spikes in an event-driven system. Event-driven vision systems use typically as sensor some bioinspired spiking device, such as the popular Dynamic Vision Sensor (DVS). DVS cameras generate spikes related to changes in light intensity. In this paper we present a 2D convolution eventdriven processing core with 128×128 pixels. S-ConvNet is an Event-Driven processing method to extract event features from an input event flow. The nature of spiking systems is highly parallel, in general. Therefore, S-ConvNet processors can benefit from the parallelism offered by Field Programmable Gate Arrays (FPGAs) to accelerate the operation. Using 3 stages of pipeline and a parallel structure, results in updating the state of a 128 neuron row in just 12ns. This improves with respect to previously reported approaches. EU grant 604102 HBP (the Human Brain Project) EU grant 644096 ECOMODE Spanish Ministry of Economy and Competitivity / European Regional Development Fund BIOSENSE TEC2012-37868-C04-02/01 Junta de Andalucía (España) NANO-NEURO TIC-6091 EU CHIST-ERA grant PNEUMA (PRI-PIMCHI-2011-0768) |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|