arrow
返回

An FPGA-Based Massively Parallel Neuromorphic Cortex Simulator

delete2018-04-10
delete39
delete
OA
AI
R
Runchun M. Wang *
C
Chetan Singh Thakur
A
André van Schaik
DOI:10.3389/fnins.2018.00213delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
This paper presents a massively parallel and scalable neuromorphic cortex simulator designed for simulating large and structurally connected spiking neural networks, such as complex models of various areas of the cortex. The main novelty of this work is the abstraction of a neuromorphic architecture into clusters represented by minicolumns and hypercolumns, analogously to the fundamental structural units observed in neurobiology. Without this approach, simulating large-scale fully connected networks needs prohibitively large memory to store look-up tables for point-to-point connections. Instead, we use a novel architecture, based on the structural connectivity in the neocortex, such that all the required parameters and connections can be stored in on-chip memory. The cortex simulator can be easily reconfigured for simulating different neural networks without any change in hardware structure by programming the memory. A hierarchical communication scheme allows one neuron to have a fan-out of up to 200k neurons. As a proof-of-concept, an implementation on one Altera Stratix V FPGA was able to simulate 20 million to 2.6 billion leaky-integrate-and-fire (LIF) neurons in real time. We verified the system by emulating a simplified auditory cortex (with 100 million neurons). This cortex simulator achieved a low power dissipation of 1.62 mu W per neuron. With the advent of commercially available FPGA boards, our system offers an accessible and scalable tool for the design, real-time simulation, and analysis of large-scale spiking neural networks.
Keyword:
neuromorphic engineering
neocortex
spiking neural networks
computational neuroscience
stochastic computing
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Frontiers in Neuroscience 封面图
Frontiers in Neuroscience
IF:
3.2
论文数:
1.6W
被引数:
5.3W

机构

I
indian institute of science (iisc) - bangalore
学者数:
1.4W
论文数: 1.4W
被引数: 11
W
western sydney university
学者数:
1.0W
论文数: 1.1W
被引数: 16
引用论文

引用论文

Alterations of cAMP response element-binding activity in the aged rat brain in response to administration of rolipram, a cAMP-specific phosphodiesterase inhibitor
err1996-09-01
err0
PREAI
errMasato Asanuma; Sakiko Nishibayashi; Emi Iwata; Yoichi Kondo; Tohru Nakanishi; Marvin Gómez Vargas; Norio Ogawa
err分享
err收藏
Voxel-based morphometry to discriminate early Alzheimer's disease from controls
err2005-07-01
err0
PREAI
errYoko Hirata; Hiroshi Matsuda; Kiyotaka Nemoto; Takashi Ohnishi; Kentaro Hirao; Fumio Yamashita; Takashi Asada; Satoshi Iwabuchi; Hirotsugu Samejima
err分享
err收藏
Challenges for large-scale implementations of spiking neural networks on FPGAs在fpga上大规模实现脉冲神经网络的挑战
err2007-12-01
err145
PREAI
errMaguire, L. P.; McGinnity, T. M.; Glackin, B.; Ghani, A.; Belatreche, A.; Harkin, J.
err分享
err收藏
Fracture of niobium hydride
err1980-09-01
err0
PREAI
errS. Gahr; B.J. Makenas; H.K. Birnbaum
err分享
err收藏
A neuromorphic implementation of multiple spike-timing synaptic plasticity rules for large-scale neural networks
err2015-05-20
err30
errOAAI
errWang, Runchun M.; Hamilton, Tara J.; Tapson, Jonathan C.; van Schaik, Andre
err分享
err收藏
学者 查看更多内容