SNNM: A Neural Simulator Based on GPU Toolbox of MatLab

摘要：

Brain, as the most important organ of human, is very complicated and is known little. For conquering the disease of brain and understanding the human intelligence, new disciplines named SNN (spiking neural networks) simulation emerged. Whereas most SNN simulator designed in C or C++ language and used by a self-defined language, it is hard to use for ordinary neural scientist. In this paper, a new SNN simulator, named SNNM (Simulator for spiking Neural Networks in MatLab) is designed by MatLab language, a facilitative modeling interface and result displaying function is designed. Furthermore, GPU (Graphic Processing Unit) is used for accelerating the execution of simulation in SNNM. An experimental evaluation shows that SNNM consistently and significantly outperform existing state-of-theart simulators.

关键词： SNMM spiking neural networks MatLab GPU

作者: Baida Zhang Junjie Wu Linqi Huang

作者单位: School of Computer, National University of Defense Technology- National laboratory for Parallel and Central South University School of Resources and Safety Engineering Changsha, China

会议类型: 国际会议

会议名称: 2011 3rd International Conference on Computer Engineering and Applications(2011第三届计算机工程与应用国际会议 ICCEA2011)

会议地点: 海口

会议语种:英文

页码: 426-430

在线出版日期: 2011-07-15（万方平台首次上网日期，不代表论文的发表时间）