Spiking neural network simulation:memory-optimal synaptic event scheduling

Robert D. Stewart; Kevin N. Gurney

首页> 外文期刊>Journal of Computational Neuroscience >Spiking neural network simulation:memory-optimal synaptic event scheduling

【24h】

Spiking neural network simulation:memory-optimal synaptic event scheduling

机译：尖峰神经网络仿真：记忆最优突触事件调度

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

Spiking neural network simulations incorporating variable transmission delays require synaptic events to be scheduled prior to delivery. Conventional methods have memory requirements that scale with the total number of synapses in a network. We introduce novel scheduling algorithms for both discrete and continuous event delivery, where the memory requirement scales instead with the number of neurons. Superior algorithmic performance is demonstrated using large-scale, benchmarking network simulations.

机译：包含可变传输延迟的尖峰神经网络仿真要求在交付之前安排突触事件的时间。常规方法具有与网络中突触的总数成比例的存储器需求。我们针对离散事件和连续事件传递引入了新颖的调度算法，其中记忆需求随神经元数量的增加而缩放。使用大规模基准网络仿真证明了优异的算法性能。

著录项

来源
《Journal of Computational Neuroscience》 |2011年第3期|p.721-728|共8页
作者
Robert D. Stewart; Kevin N. Gurney;
展开▼
作者单位

MRC Anatomical Neuropharmacology Unit,Mansfield Road, Oxford, OX1 3TH, UK;

Department of Psychology, University of Sheffield,Sheffield, S10 2TP, UK;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类
关键词
spiking neural network; synaptic event; izhikevich;

机译：尖刺神经网络;突触事件;izhikevich;

相似文献

外文文献
中文文献
专利

1. Dynamic parallelism for synaptic updating in GPU-accelerated spiking neural network simulations [J] . Kasap Bahadir, van Opstal A. John Neurocomputing . 2018,第AUGa9期

机译：GPU加速尖峰神经网络仿真中用于突触更新的动态并行性
2. Determinants of associative memory performance in spiking and non-spiking neural networks with different synaptic plasticity regimes [J] . Alex Metaxas, Reinoud Maex, Rod Adams, BMC Neuroscience . 2012,第SUPPLEMENTa1期

机译：具有不同突触可塑性机制的尖峰和非尖峰神经网络中联想记忆性能的决定因素
3. Hardware event-driven simulation engine for spiking neural networks [J] . R. AGIS, E. ROS, J. DIAZ, International journal of electronics . 2007,第5期

机译：硬件事件驱动的仿真引擎，用于增强神经网络
4. Validation of Spiking Neural Networks Using Resistive-Switching Synaptic Device with Spike-Rate-Dependent Plasticity [C] . Suhyun Bang, Min-Hye Oh, Min-Hwi Kim, International Conference on Electronics, Information, and Communication . 2020

机译：使用具有速率依赖性的可塑性的电阻切换突触设备验证尖峰神经网络
5. The Role of Short-Term Synaptic Plasticity in Neural Network Spiking Dynamics and in the Learning of Multiple Distal Rewards. [D] . O'Brien, Michael John. 2013

机译：短期突触可塑性在神经网络突增动力学和多重远距学习中的作用。
6. Dynamic parallelism for synaptic updating in GPU-accelerated spiking neural network simulations [O] . Bahadir Kasap, A. John van Opstal -1

机译：GPU加速尖峰神经网络仿真中用于突触更新的动态并行性
7. Determinants of associative memory performance in spiking and non-spiking neural networks with different synaptic plasticity regimes [O] . Alex Metaxas, Reinoud Maex, Rod Adams, 2013

机译：具有不同突触可塑性机制的尖峰和非尖峰神经网络中联想记忆性能的决定因素

Spiking neural network simulation:memory-optimal synaptic event scheduling

摘要

著录项

相似文献

相关主题

期刊订阅