A neuromorphic neural spike clustering processor for deep-brain sensing and stimulation systems

Beinuo Zhang; Zhewei Jiang; Qi Wang; Jae-sun Seo; Mingoo Seok

doi:10.1109/ISLPED.2015.7273496

A neuromorphic neural spike clustering processor for deep-brain sensing and stimulation systems

Beinuo Zhang, Zhewei Jiang, Qi Wang, Jae-sun Seo, Mingoo Seok

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

5 Scopus citations

Abstract

This paper presents algorithm and digital hardware design, inspired by biological spiking neural networks, to perform unsupervised, online spike-clustering with high accuracy and low-power consumption in the context of deep-brain sensing and stimulation systems. The proposed hardware contains 1220 digital neurons and 4.86k latch-based synapses, and achieves the average sorting accuracy of 91% whereas the conventional hardware based on the Osort algorithm achieves 69% for the same datasets. Implemented in a 65nm high-V_th, the processor exhibits a footprint of 0.25mm²/ch. and a power consumption of 9.3μW/ch. at V_DD of 0.3V.

Original language	English (US)
Title of host publication	Proceedings of the International Symposium on Low Power Electronics and Design
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	91-97
Number of pages	7
Volume	2015-September
ISBN (Print)	9781467380096
DOIs	https://doi.org/10.1109/ISLPED.2015.7273496
State	Published - Sep 21 2015
Event	20th IEEE/ACM International Symposium on Low Power Electronics and Design, ISLPED 2015 - Rome, Italy Duration: Jul 22 2015 → Jul 24 2015

Other

Other	20th IEEE/ACM International Symposium on Low Power Electronics and Design, ISLPED 2015
Country	Italy
City	Rome
Period	7/22/15 → 7/24/15

Keywords

Accuracy
Clustering algorithms
Encoding
Firing
Hardware
Neurons
Training

ASJC Scopus subject areas

Engineering(all)

Access to Document

10.1109/ISLPED.2015.7273496

Fingerprint Dive into the research topics of 'A neuromorphic neural spike clustering processor for deep-brain sensing and stimulation systems'. Together they form a unique fingerprint.

Cite this

Zhang, B., Jiang, Z., Wang, Q., Seo, J., & Seok, M. (2015). A neuromorphic neural spike clustering processor for deep-brain sensing and stimulation systems. In Proceedings of the International Symposium on Low Power Electronics and Design (Vol. 2015-September, pp. 91-97). [7273496] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISLPED.2015.7273496

A neuromorphic neural spike clustering processor for deep-brain sensing and stimulation systems. / Zhang, Beinuo; Jiang, Zhewei; Wang, Qi; Seo, Jae-sun; Seok, Mingoo.

Proceedings of the International Symposium on Low Power Electronics and Design. Vol. 2015-September Institute of Electrical and Electronics Engineers Inc., 2015. p. 91-97 7273496.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Zhang, B, Jiang, Z, Wang, Q, Seo, J & Seok, M 2015, A neuromorphic neural spike clustering processor for deep-brain sensing and stimulation systems. in Proceedings of the International Symposium on Low Power Electronics and Design. vol. 2015-September, 7273496, Institute of Electrical and Electronics Engineers Inc., pp. 91-97, 20th IEEE/ACM International Symposium on Low Power Electronics and Design, ISLPED 2015, Rome, Italy, 7/22/15. https://doi.org/10.1109/ISLPED.2015.7273496

@inproceedings{32515d7c4ed54f508cdeadec0b48e4af,

title = "A neuromorphic neural spike clustering processor for deep-brain sensing and stimulation systems",

abstract = "This paper presents algorithm and digital hardware design, inspired by biological spiking neural networks, to perform unsupervised, online spike-clustering with high accuracy and low-power consumption in the context of deep-brain sensing and stimulation systems. The proposed hardware contains 1220 digital neurons and 4.86k latch-based synapses, and achieves the average sorting accuracy of 91% whereas the conventional hardware based on the Osort algorithm achieves 69% for the same datasets. Implemented in a 65nm high-Vth, the processor exhibits a footprint of 0.25mm2/ch. and a power consumption of 9.3μW/ch. at VDD of 0.3V.",

keywords = "Accuracy, Clustering algorithms, Encoding, Firing, Hardware, Neurons, Training",

author = "Beinuo Zhang and Zhewei Jiang and Qi Wang and Jae-sun Seo and Mingoo Seok",

year = "2015",

month = sep,

day = "21",

doi = "10.1109/ISLPED.2015.7273496",

language = "English (US)",

isbn = "9781467380096",

volume = "2015-September",

pages = "91--97",

booktitle = "Proceedings of the International Symposium on Low Power Electronics and Design",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "20th IEEE/ACM International Symposium on Low Power Electronics and Design, ISLPED 2015 ; Conference date: 22-07-2015 Through 24-07-2015",

}

TY - GEN

T1 - A neuromorphic neural spike clustering processor for deep-brain sensing and stimulation systems

AU - Zhang, Beinuo

AU - Jiang, Zhewei

AU - Wang, Qi

AU - Seo, Jae-sun

AU - Seok, Mingoo

PY - 2015/9/21

Y1 - 2015/9/21

N2 - This paper presents algorithm and digital hardware design, inspired by biological spiking neural networks, to perform unsupervised, online spike-clustering with high accuracy and low-power consumption in the context of deep-brain sensing and stimulation systems. The proposed hardware contains 1220 digital neurons and 4.86k latch-based synapses, and achieves the average sorting accuracy of 91% whereas the conventional hardware based on the Osort algorithm achieves 69% for the same datasets. Implemented in a 65nm high-Vth, the processor exhibits a footprint of 0.25mm2/ch. and a power consumption of 9.3μW/ch. at VDD of 0.3V.

AB - This paper presents algorithm and digital hardware design, inspired by biological spiking neural networks, to perform unsupervised, online spike-clustering with high accuracy and low-power consumption in the context of deep-brain sensing and stimulation systems. The proposed hardware contains 1220 digital neurons and 4.86k latch-based synapses, and achieves the average sorting accuracy of 91% whereas the conventional hardware based on the Osort algorithm achieves 69% for the same datasets. Implemented in a 65nm high-Vth, the processor exhibits a footprint of 0.25mm2/ch. and a power consumption of 9.3μW/ch. at VDD of 0.3V.

KW - Accuracy

KW - Clustering algorithms

KW - Encoding

KW - Firing

KW - Hardware

KW - Neurons

KW - Training

UR - http://www.scopus.com/inward/record.url?scp=84958524185&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84958524185&partnerID=8YFLogxK

U2 - 10.1109/ISLPED.2015.7273496

DO - 10.1109/ISLPED.2015.7273496

M3 - Conference contribution

AN - SCOPUS:84958524185

SN - 9781467380096

VL - 2015-September

SP - 91

EP - 97

BT - Proceedings of the International Symposium on Low Power Electronics and Design

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 20th IEEE/ACM International Symposium on Low Power Electronics and Design, ISLPED 2015

Y2 - 22 July 2015 through 24 July 2015

ER -