Neuromorphic Self-Organizing Map Design for Classification of Bioelectric-Timescale Signals

J. Mes; E. Stienstra; X.F. You; S.S. Kumar; A. Zjajo; C. Galuzzi; R. van Leuken

doi:10.1109/SAMOS.2017.8344618

Neuromorphic Self-Organizing Map Design for Classification of Bioelectric-Timescale Signals

J. Mes^*, E. Stienstra, X.F. You, S.S. Kumar, A. Zjajo, C. Galuzzi, R. van Leuken

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

Abstract

The Self-Organizing Map (SOM) is a recurrent neural network topology that realizes competitive learning for the unsupervised classification of data. In this paper, we investigate the design of a spiking neural network-based SOM for the classification of bioelectric-timescale signals. We present novel insights into the architectural design space, inherent trade-offs, and the critical requirements for designing and configuring neurons, synapses and learning rules to achieve stable and accurate behaviour. We perform this exploration using high-level architectural simulations and, additionally, through the full-custom implementation of components.

Original language	English
Title of host publication	INTERNATIONAL CONFERENCE ON EMBEDDED COMPUTER SYSTEMS: ARCHITECTURES, MODELING, AND SIMULATION (SAMOS 2017)
Publisher	IEEE
Pages	113-120
Number of pages	8
ISBN (Print)	9781538634370
DOIs	https://doi.org/10.1109/SAMOS.2017.8344618
Publication status	Published - Jul 2017
Event	17th Annual International Conference on Embedded Computer Systems - Architectures, Modeling, and Simulation (SAMOS) - Samos, Greece Duration: 16 Jul 2017 → 20 Jul 2017 https://cps-vo.org/node/32674

Conference

Conference	17th Annual International Conference on Embedded Computer Systems - Architectures, Modeling, and Simulation (SAMOS)
Country/Territory	Greece
City	Samos
Period	16/07/17 → 20/07/17
Internet address	https://cps-vo.org/node/32674

Keywords

NEURAL-NETWORK
SYNAPTIC PLASTICITY
SPIKING NEURONS
MODEL
COMPUTATION
SYNAPSES

Access to Document

10.1109/SAMOS.2017.8344618

Cite this

@inproceedings{0dc533be960b43a1a74d650b9a506630,

title = "Neuromorphic Self-Organizing Map Design for Classification of Bioelectric-Timescale Signals",

abstract = "The Self-Organizing Map (SOM) is a recurrent neural network topology that realizes competitive learning for the unsupervised classification of data. In this paper, we investigate the design of a spiking neural network-based SOM for the classification of bioelectric-timescale signals. We present novel insights into the architectural design space, inherent trade-offs, and the critical requirements for designing and configuring neurons, synapses and learning rules to achieve stable and accurate behaviour. We perform this exploration using high-level architectural simulations and, additionally, through the full-custom implementation of components.",

keywords = "NEURAL-NETWORK, SYNAPTIC PLASTICITY, SPIKING NEURONS, MODEL, COMPUTATION, SYNAPSES",

author = "J. Mes and E. Stienstra and X.F. You and S.S. Kumar and A. Zjajo and C. Galuzzi and {van Leuken}, R.",

year = "2017",

month = jul,

doi = "10.1109/SAMOS.2017.8344618",

language = "English",

isbn = "9781538634370",

pages = "113--120",

booktitle = "INTERNATIONAL CONFERENCE ON EMBEDDED COMPUTER SYSTEMS: ARCHITECTURES, MODELING, AND SIMULATION (SAMOS 2017)",

publisher = "IEEE",

address = "United States",

note = "17th Annual International Conference on Embedded Computer Systems - Architectures, Modeling, and Simulation (SAMOS) ; Conference date: 16-07-2017 Through 20-07-2017",

url = "https://cps-vo.org/node/32674",

}

Mes, J, Stienstra, E, You, XF, Kumar, SS, Zjajo, A, Galuzzi, C & van Leuken, R 2017, Neuromorphic Self-Organizing Map Design for Classification of Bioelectric-Timescale Signals. in INTERNATIONAL CONFERENCE ON EMBEDDED COMPUTER SYSTEMS: ARCHITECTURES, MODELING, AND SIMULATION (SAMOS 2017). IEEE, pp. 113-120, 17th Annual International Conference on Embedded Computer Systems - Architectures, Modeling, and Simulation (SAMOS), Samos, Greece, 16/07/17. https://doi.org/10.1109/SAMOS.2017.8344618

Neuromorphic Self-Organizing Map Design for Classification of Bioelectric-Timescale Signals. / Mes, J.; Stienstra, E.; You, X.F. et al.
INTERNATIONAL CONFERENCE ON EMBEDDED COMPUTER SYSTEMS: ARCHITECTURES, MODELING, AND SIMULATION (SAMOS 2017). IEEE, 2017. p. 113-120.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

TY - GEN

T1 - Neuromorphic Self-Organizing Map Design for Classification of Bioelectric-Timescale Signals

AU - Mes, J.

AU - Stienstra, E.

AU - You, X.F.

AU - Kumar, S.S.

AU - Zjajo, A.

AU - Galuzzi, C.

AU - van Leuken, R.

PY - 2017/7

Y1 - 2017/7

N2 - The Self-Organizing Map (SOM) is a recurrent neural network topology that realizes competitive learning for the unsupervised classification of data. In this paper, we investigate the design of a spiking neural network-based SOM for the classification of bioelectric-timescale signals. We present novel insights into the architectural design space, inherent trade-offs, and the critical requirements for designing and configuring neurons, synapses and learning rules to achieve stable and accurate behaviour. We perform this exploration using high-level architectural simulations and, additionally, through the full-custom implementation of components.

AB - The Self-Organizing Map (SOM) is a recurrent neural network topology that realizes competitive learning for the unsupervised classification of data. In this paper, we investigate the design of a spiking neural network-based SOM for the classification of bioelectric-timescale signals. We present novel insights into the architectural design space, inherent trade-offs, and the critical requirements for designing and configuring neurons, synapses and learning rules to achieve stable and accurate behaviour. We perform this exploration using high-level architectural simulations and, additionally, through the full-custom implementation of components.

KW - NEURAL-NETWORK

KW - SYNAPTIC PLASTICITY

KW - SPIKING NEURONS

KW - MODEL

KW - COMPUTATION

KW - SYNAPSES

U2 - 10.1109/SAMOS.2017.8344618

DO - 10.1109/SAMOS.2017.8344618

M3 - Conference article in proceeding

SN - 9781538634370

SP - 113

EP - 120

BT - INTERNATIONAL CONFERENCE ON EMBEDDED COMPUTER SYSTEMS: ARCHITECTURES, MODELING, AND SIMULATION (SAMOS 2017)

PB - IEEE

T2 - 17th Annual International Conference on Embedded Computer Systems - Architectures, Modeling, and Simulation (SAMOS)

Y2 - 16 July 2017 through 20 July 2017

ER -