Three Tools for the Real-Time Simulation of Embodied Spiking Neural Networks Using GPUs

被引：4

作者：

Fidjeland, Andreas K. ^{[1
]}

Gamez, David ^{[1
]}

Shanahan, Murray P. ^{[1
]}

Lazdins, Edgars ^{[1
]}

机构：

[1] Univ London Imperial Coll Sci Technol & Med, London SW7 2AZ, England

来源：

NEUROINFORMATICS | 2013年 / 11卷 / 03期

基金：

英国工程与自然科学研究理事会;

关键词：

Simulation; 3D visualization; Spike encoding; Robotics; Spiking neural networks; iCub; GPU; 2-DIMENSIONAL LIMB MOVEMENTS; MUSCLE-SPINDLE FEEDBACK; NEURONS; BRAIN; INFORMATION; HUMANS; MODEL; SKIN; ARCHITECTURE; AFFERENTS;

D O I：

10.1007/s12021-012-9174-x

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

This paper presents a toolbox of solutions that enable the user to construct biologically-inspired spiking neural networks with tens of thousands of neurons and millions of connections that can be simulated in real time, visualized in 3D and connected to robots and other devices. NeMo is a high performance simulator that works with a variety of neural and oscillator models and performs parallel simulations on either GPUs or multi-core processors. SpikeStream is a visualization and analysis environment that works with NeMo and can construct networks, store them in a database and visualize their activity in 3D. The iSpike library provides biologically-inspired conversion between real data and spike representations to support work with robots, such as the iCub. Each of the tools described in this paper can be used independently with other software, and they also work well together.

引用

页码：267 / 290

页数：24

共 50 条

[1] Three Tools for the Real-Time Simulation of Embodied Spiking Neural Networks Using GPUs
Andreas K. Fidjeland
David Gamez
Murray P. Shanahan
Edgars Lazdins
Neuroinformatics, 2013, 11 : 267 - 290
[2] Accelerated Simulation of Spiking Neural Networks Using GPUs
Fidjeland, Andreas K.
Shanahan, Murray P.
2010 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS IJCNN 2010, 2010,
[3] Real-Time Classification of Multivariate Olfaction Data Using Spiking Neural Networks
Vanarse, Anup
Osseiran, Adam
Rassau, Alexander
SENSORS, 2019, 19 (08):
[4] A generalized hardware architecture for real-time spiking neural networks
Valencia, Daniel
Alimohammad, Amir
NEURAL COMPUTING & APPLICATIONS, 2023, 35 (24): : 17821 - 17835
[5] A generalized hardware architecture for real-time spiking neural networks
Daniel Valencia
Amir Alimohammad
Neural Computing and Applications, 2023, 35 : 17821 - 17835
[6] An FPGA Platform for Real-Time Simulation of Spiking Neuronal Networks
Pani, Danilo
Meloni, Paolo
Tuveri, Giuseppe
Palumbo, Francesca
Massobrio, Paolo
Raffo, Luigi
FRONTIERS IN NEUROSCIENCE, 2017, 11
[7] GPU-Based Simulation of Spiking Neural Networks with Real-Time Performance & High Accuracy
Yudanov, Dmitri
Shaaban, Muhammad
Melton, Roy
Reznik, Leon
2010 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS IJCNN 2010, 2010,
[8] Real-time classification of LIDAR data using discrete-time Recurrent Spiking Neural Networks
Vicol, Anca-Diana
Yin, Bojian
Bohte, Sander M.
2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2022,
[9] Spacecraft real-time thermal simulation using artificial neural networks
J. D. Reis Junior
A. M. Ambrosio
F. L. de Sousa
D. F. Silva
Journal of the Brazilian Society of Mechanical Sciences and Engineering, 2021, 43
[10] Adaptive real-time control flight simulation using neural networks
Chen, H
Wan, TR
Earnshaw, RA
GAME-ON 2004: 5th International Conference on Intelligent Games and Simulation, 2004, : 71 - 75

← 1 2 3 4 5 →