A biologically plausible real-time spiking neuron simulation environment based on a multiple-FPGA platform

Yang, S. and McGinnity, T.M. (2011) A biologically plausible real-time spiking neuron simulation environment based on a multiple-FPGA platform. Computer Architecture News, 39(4), pp. 78-81. (doi: 10.1145/2082156.2082176)

Abstract

Neurological research has revealed that neurons encode information in the timing of spikes. Spiking neural network simulations are a flexible and powerful method for investigating the behaviour of such neuronal systems. The spiking neuron models which are used in simulations can be described mathematically, but the continuous time involved in mathematical models needs to be replaced by discrete time steps. An alternative approach, hardware implementation, provides the possibility of generating independent spikes precisely and simultaneously output spike waves in real biological time, under the premise that the spiking neural network implemented in hardware can take full advantage of hardware-timed speed and reliability. In this work we propose a multi-layered biologically plausible real-time spiking neural network simulation platform that can be used to emulate the operation of biological neural systems (such as elements of the visual cortex) and computational models of such systems. The implementation of a layered spiking neural network using the Xilinx Virtex-4 family of Field Programmable Gate Array (FPGA) is presented.

• Item Type: Articles
• Additional Information: Dr. Yang is supported under the Centre of Excellence in Intelligent Systems (CoEIS) project, funded by InvestNI, and the Integrated Development Fund through ILEX.
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Yang, Dr Shufan
• Authors: Yang, S., and McGinnity, T.M.
• College/School: College of Science and Engineering > School of Engineering > Systems Power and Energy
• Journal Name: Computer Architecture News
• Publisher: ACM
• ISSN: 0163-5964
• ISSN (Online): 1943-5851