Energy-Efficient Multipath Ring Network for Heterogeneous Clustered Neuronal Arrays

Andrei Ardelean; Amir Zjajo; Sumeet Kumar; Rene van Leuken

doi:10.1109/BHI.2018.8333401

Energy-Efficient Multipath Ring Network for Heterogeneous Clustered Neuronal Arrays

Andrei Ardelean^*, Amir Zjajo, Sumeet Kumar, Rene van Leuken

^*Corresponding author for this work

Signal Processing Systems

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

Abstract

Simulating large spiking neural networks with a high level of realism in a FPGA requires efficient network architectures that satisfy both the resource and interconnect constraints, as well as the changes in traffic patterns due to learning processes. In this paper, we propose a dataflow architecture based on a multipath ring topology that offers traffic shaping capabilities, and high energy-efficiency for the neuron-to-neuron communications.

Original language	English
Title of host publication	2018 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI)
Publisher	IEEE
Pages	190-193
Number of pages	4
ISBN (Electronic)	978-1-5386-2405-0
ISBN (Print)	978-1-5386-2406-7
DOIs	https://doi.org/10.1109/BHI.2018.8333401
Publication status	Published - 2018
Event	2018 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2018 - Las Vegas, United States Duration: 4 Mar 2018 → 7 Mar 2018

Conference

Conference	2018 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2018
Country/Territory	United States
City	Las Vegas
Period	4/03/18 → 7/03/18

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/BHI.2018.8333401

Cite this

@inproceedings{f2afdd7330514a6abe1d4698bdcc1e07,

title = "Energy-Efficient Multipath Ring Network for Heterogeneous Clustered Neuronal Arrays",

abstract = "Simulating large spiking neural networks with a high level of realism in a FPGA requires efficient network architectures that satisfy both the resource and interconnect constraints, as well as the changes in traffic patterns due to learning processes. In this paper, we propose a dataflow architecture based on a multipath ring topology that offers traffic shaping capabilities, and high energy-efficiency for the neuron-to-neuron communications.",

author = "Andrei Ardelean and Amir Zjajo and Sumeet Kumar and {van Leuken}, Rene",

year = "2018",

doi = "10.1109/BHI.2018.8333401",

language = "English",

isbn = "978-1-5386-2406-7 ",

pages = "190--193",

booktitle = "2018 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI)",

publisher = "IEEE",

address = "United States",

note = "2018 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2018 ; Conference date: 04-03-2018 Through 07-03-2018",

}

Ardelean, A, Zjajo, A, Kumar, S & van Leuken, R 2018, Energy-Efficient Multipath Ring Network for Heterogeneous Clustered Neuronal Arrays. in 2018 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI) . IEEE, pp. 190-193, 2018 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2018, Las Vegas, United States, 4/03/18. https://doi.org/10.1109/BHI.2018.8333401

Energy-Efficient Multipath Ring Network for Heterogeneous Clustered Neuronal Arrays. / Ardelean, Andrei; Zjajo, Amir; Kumar, Sumeet et al.
2018 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI) . IEEE, 2018. p. 190-193.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Energy-Efficient Multipath Ring Network for Heterogeneous Clustered Neuronal Arrays

AU - Ardelean, Andrei

AU - Zjajo, Amir

AU - Kumar, Sumeet

AU - van Leuken, Rene

PY - 2018

Y1 - 2018

N2 - Simulating large spiking neural networks with a high level of realism in a FPGA requires efficient network architectures that satisfy both the resource and interconnect constraints, as well as the changes in traffic patterns due to learning processes. In this paper, we propose a dataflow architecture based on a multipath ring topology that offers traffic shaping capabilities, and high energy-efficiency for the neuron-to-neuron communications.

AB - Simulating large spiking neural networks with a high level of realism in a FPGA requires efficient network architectures that satisfy both the resource and interconnect constraints, as well as the changes in traffic patterns due to learning processes. In this paper, we propose a dataflow architecture based on a multipath ring topology that offers traffic shaping capabilities, and high energy-efficiency for the neuron-to-neuron communications.

UR - http://www.scopus.com/inward/record.url?scp=85050864291&partnerID=8YFLogxK

U2 - 10.1109/BHI.2018.8333401

DO - 10.1109/BHI.2018.8333401

M3 - Conference contribution

AN - SCOPUS:85050864291

SN - 978-1-5386-2406-7

SP - 190

EP - 193

BT - 2018 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI)

PB - IEEE

T2 - 2018 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2018

Y2 - 4 March 2018 through 7 March 2018

ER -

Energy-Efficient Multipath Ring Network for Heterogeneous Clustered Neuronal Arrays

Abstract

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this