Silicon spiking neurons for hardware implementation of extreme learning machines

Arindam Basu; Sun Shuo; Hongming Zhou; Meng Hiot Lim; Guang-Bin Huang

doi:10.1016/j.neucom.2012.01.042

Silicon spiking neurons for hardware implementation of extreme learning machines

Arindam Basu
, Sun Shuo
, Hongming Zhou
, Meng Hiot Lim
, Guang-Bin Huang

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

70 Citations (Scopus)

Abstract

In this paper, we propose a silicon implementation of extreme learning machines (ELM) using spiking neural circuits. The major components of a silicon spiking neural network, neuron, synapse and 'Address Event Representation' (AER) for asynchronous spike based communication, are described. The benefits of using this hardware to implement an ELM as opposed to other single layer feedforward networks (SLFN) are explained. Several possible architectures for efficient implementation of ELM using these circuits are presented and their possible impact on ELM performance is discussed. © 2012 Elsevier B.V.

Original language	English
Pages (from-to)	125-134
Journal	Neurocomputing
Volume	102
DOIs	https://doi.org/10.1016/j.neucom.2012.01.042
Publication status	Published - 15 Feb 2013
Externally published	Yes

Bibliographical note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

Research Keywords

Asynchronous communication
Extreme learning machine
Neuromorphic
Silicon neuron
Spiking neural network

Access Output

10.1016/j.neucom.2012.01.042

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{3ec686291ba64375a923494ea31d5f68,

title = "Silicon spiking neurons for hardware implementation of extreme learning machines",

abstract = "In this paper, we propose a silicon implementation of extreme learning machines (ELM) using spiking neural circuits. The major components of a silicon spiking neural network, neuron, synapse and 'Address Event Representation' (AER) for asynchronous spike based communication, are described. The benefits of using this hardware to implement an ELM as opposed to other single layer feedforward networks (SLFN) are explained. Several possible architectures for efficient implementation of ELM using these circuits are presented and their possible impact on ELM performance is discussed. {\textcopyright} 2012 Elsevier B.V.",

keywords = "Asynchronous communication, Extreme learning machine, Neuromorphic, Silicon neuron, Spiking neural network",

author = "Arindam Basu and Sun Shuo and Hongming Zhou and \{Hiot Lim\}, Meng and Guang-Bin Huang",

note = "Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].",

year = "2013",

month = feb,

day = "15",

doi = "10.1016/j.neucom.2012.01.042",

language = "English",

volume = "102",

pages = "125--134",

journal = "Neurocomputing",

issn = "0925-2312",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Silicon spiking neurons for hardware implementation of extreme learning machines

AU - Basu, Arindam

AU - Shuo, Sun

AU - Zhou, Hongming

AU - Hiot Lim, Meng

AU - Huang, Guang-Bin

N1 - Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

PY - 2013/2/15

Y1 - 2013/2/15

N2 - In this paper, we propose a silicon implementation of extreme learning machines (ELM) using spiking neural circuits. The major components of a silicon spiking neural network, neuron, synapse and 'Address Event Representation' (AER) for asynchronous spike based communication, are described. The benefits of using this hardware to implement an ELM as opposed to other single layer feedforward networks (SLFN) are explained. Several possible architectures for efficient implementation of ELM using these circuits are presented and their possible impact on ELM performance is discussed. © 2012 Elsevier B.V.

AB - In this paper, we propose a silicon implementation of extreme learning machines (ELM) using spiking neural circuits. The major components of a silicon spiking neural network, neuron, synapse and 'Address Event Representation' (AER) for asynchronous spike based communication, are described. The benefits of using this hardware to implement an ELM as opposed to other single layer feedforward networks (SLFN) are explained. Several possible architectures for efficient implementation of ELM using these circuits are presented and their possible impact on ELM performance is discussed. © 2012 Elsevier B.V.

KW - Asynchronous communication

KW - Extreme learning machine

KW - Neuromorphic

KW - Silicon neuron

KW - Spiking neural network

UR - https://www.scopus.com/pages/publications/84870252936

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-84870252936&origin=recordpage

U2 - 10.1016/j.neucom.2012.01.042

DO - 10.1016/j.neucom.2012.01.042

M3 - RGC 21 - Publication in refereed journal

SN - 0925-2312

VL - 102

SP - 125

EP - 134

JO - Neurocomputing

JF - Neurocomputing

ER -

Silicon spiking neurons for hardware implementation of extreme learning machines

Abstract

Bibliographical note

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this