Lateral inhibitory networks: Synchrony, edge enhancement, and noise reduction

C. Glackin; L. Maguire; L. McDaid; J. Wade

doi:10.1109/IJCNN.2011.6033332

Lateral inhibitory networks: Synchrony, edge enhancement, and noise reduction

C. Glackin, L. Maguire, L. McDaid, J. Wade

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

3 Citations (Scopus)

Abstract

This paper investigates how layers of spiking neurons can be connected using lateral inhibition in different ways to bring about synchrony, reduce noise, and extract or enhance features. To illustrate the effects of the various
connectivity regimes spectro-temporal speech data in the form
of isolated digits is employed. The speech samples are preprocessed
using the Lyon’s Passive Ear cochlear model, and then encoded into tonotopically arranged spike arrays using the BSA spiker algorithm. The spike arrays are then subjected to various lateral inhibitory connectivity regimes configured
by two connectivity parameters, namely connection length and
neighbourhood size. The combination of these parameters are
demonstrated to produce various effects such as transient
synchrony, reduction of noisy spikes, and sharpening of spectrotemporal
features

Original language	English
Title of host publication	Procs of the 2011 International Joint Conference on Neural Networks
Subtitle of host publication	(IJCNN)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	1003-1009
Number of pages	7
ISBN (Print)	978-1-4244-9637-2
DOIs	https://doi.org/10.1109/IJCNN.2011.6033332
Publication status	Published - 2011
Event	2011 Int Joint Conf on Neural Networks IJCNN - San Jose, United States Duration: 31 Jul 2011 → 5 Aug 2011

Conference

Conference	2011 Int Joint Conf on Neural Networks IJCNN
Country/Territory	United States
City	San Jose
Period	31/07/11 → 5/08/11

Access to Document

10.1109/IJCNN.2011.6033332

Cite this

@inproceedings{7ce7b137fc7c4c28adfd7f1048c1e769,

title = "Lateral inhibitory networks: Synchrony, edge enhancement, and noise reduction",

abstract = "This paper investigates how layers of spiking neurons can be connected using lateral inhibition in different ways to bring about synchrony, reduce noise, and extract or enhance features. To illustrate the effects of the various connectivity regimes spectro-temporal speech data in the form of isolated digits is employed. The speech samples are preprocessed using the Lyon{\textquoteright}s Passive Ear cochlear model, and then encoded into tonotopically arranged spike arrays using the BSA spiker algorithm. The spike arrays are then subjected to various lateral inhibitory connectivity regimes configured by two connectivity parameters, namely connection length and neighbourhood size. The combination of these parameters are demonstrated to produce various effects such as transient synchrony, reduction of noisy spikes, and sharpening of spectrotemporal features",

author = "C. Glackin and L. Maguire and L. McDaid and J. Wade",

year = "2011",

doi = "10.1109/IJCNN.2011.6033332",

language = "English",

isbn = "978-1-4244-9637-2",

pages = "1003--1009",

booktitle = "Procs of the 2011 International Joint Conference on Neural Networks",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

note = "2011 Int Joint Conf on Neural Networks IJCNN ; Conference date: 31-07-2011 Through 05-08-2011",

}

Glackin, C, Maguire, L, McDaid, L & Wade, J 2011, Lateral inhibitory networks: Synchrony, edge enhancement, and noise reduction. in Procs of the 2011 International Joint Conference on Neural Networks : (IJCNN). Institute of Electrical and Electronics Engineers (IEEE), pp. 1003-1009, 2011 Int Joint Conf on Neural Networks IJCNN, San Jose, United States, 31/07/11. https://doi.org/10.1109/IJCNN.2011.6033332

Lateral inhibitory networks: Synchrony, edge enhancement, and noise reduction. / Glackin, C.; Maguire, L.; McDaid, L. et al.
Procs of the 2011 International Joint Conference on Neural Networks : (IJCNN). Institute of Electrical and Electronics Engineers (IEEE), 2011. p. 1003-1009.

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

TY - GEN

T1 - Lateral inhibitory networks

T2 - 2011 Int Joint Conf on Neural Networks IJCNN

AU - Glackin, C.

AU - Maguire, L.

AU - McDaid, L.

AU - Wade, J.

PY - 2011

Y1 - 2011

N2 - This paper investigates how layers of spiking neurons can be connected using lateral inhibition in different ways to bring about synchrony, reduce noise, and extract or enhance features. To illustrate the effects of the various connectivity regimes spectro-temporal speech data in the form of isolated digits is employed. The speech samples are preprocessed using the Lyon’s Passive Ear cochlear model, and then encoded into tonotopically arranged spike arrays using the BSA spiker algorithm. The spike arrays are then subjected to various lateral inhibitory connectivity regimes configured by two connectivity parameters, namely connection length and neighbourhood size. The combination of these parameters are demonstrated to produce various effects such as transient synchrony, reduction of noisy spikes, and sharpening of spectrotemporal features

AB - This paper investigates how layers of spiking neurons can be connected using lateral inhibition in different ways to bring about synchrony, reduce noise, and extract or enhance features. To illustrate the effects of the various connectivity regimes spectro-temporal speech data in the form of isolated digits is employed. The speech samples are preprocessed using the Lyon’s Passive Ear cochlear model, and then encoded into tonotopically arranged spike arrays using the BSA spiker algorithm. The spike arrays are then subjected to various lateral inhibitory connectivity regimes configured by two connectivity parameters, namely connection length and neighbourhood size. The combination of these parameters are demonstrated to produce various effects such as transient synchrony, reduction of noisy spikes, and sharpening of spectrotemporal features

U2 - 10.1109/IJCNN.2011.6033332

DO - 10.1109/IJCNN.2011.6033332

M3 - Conference contribution

SN - 978-1-4244-9637-2

SP - 1003

EP - 1009

BT - Procs of the 2011 International Joint Conference on Neural Networks

PB - Institute of Electrical and Electronics Engineers (IEEE)

Y2 - 31 July 2011 through 5 August 2011

ER -

Lateral inhibitory networks: Synchrony, edge enhancement, and noise reduction

Abstract

Conference

Access to Document

Fingerprint

Cite this