Character recognition using spiking neural networks

Ankur Gupta; Lyle N. Long

doi:10.1109/IJCNN.2007.4370930

Character recognition using spiking neural networks

Ankur Gupta, Lyle N. Long

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

74 Scopus citations

Abstract

A spiking neural network model is used to identify characters in a character set. The network is a two layered structure consisting of integrate-and-fire and active dendrite neurons. There are both excitatory and inhibitory connections in the network. Spike time dependent plasticity (STDP) is used for training. The winner take all mechanism is enforced by the lateral inhibitory connections. It is found that most of the characters are recognized in a character set consisting of 48 characters. The network is trained successfully with increased resolution of the characters. Also, addition of uniform random noise does not decrease its recognition capability.

Original language	English (US)
Title of host publication	The 2007 International Joint Conference on Neural Networks, IJCNN 2007 Conference Proceedings
Pages	53-58
Number of pages	6
DOIs	https://doi.org/10.1109/IJCNN.2007.4370930
State	Published - 2007
Event	2007 International Joint Conference on Neural Networks, IJCNN 2007 - Orlando, FL, United States Duration: Aug 12 2007 → Aug 17 2007

Publication series

Name	IEEE International Conference on Neural Networks - Conference Proceedings
ISSN (Print)	1098-7576

Other

Other	2007 International Joint Conference on Neural Networks, IJCNN 2007
Country/Territory	United States
City	Orlando, FL
Period	8/12/07 → 8/17/07

All Science Journal Classification (ASJC) codes

Software

Access to Document

10.1109/IJCNN.2007.4370930

Cite this

@inproceedings{9c321c1b14894c53975b3c8e77cc2555,

title = "Character recognition using spiking neural networks",

abstract = "A spiking neural network model is used to identify characters in a character set. The network is a two layered structure consisting of integrate-and-fire and active dendrite neurons. There are both excitatory and inhibitory connections in the network. Spike time dependent plasticity (STDP) is used for training. The winner take all mechanism is enforced by the lateral inhibitory connections. It is found that most of the characters are recognized in a character set consisting of 48 characters. The network is trained successfully with increased resolution of the characters. Also, addition of uniform random noise does not decrease its recognition capability.",

author = "Ankur Gupta and Long, {Lyle N.}",

year = "2007",

doi = "10.1109/IJCNN.2007.4370930",

language = "English (US)",

isbn = "142441380X",

series = "IEEE International Conference on Neural Networks - Conference Proceedings",

pages = "53--58",

booktitle = "The 2007 International Joint Conference on Neural Networks, IJCNN 2007 Conference Proceedings",

note = "2007 International Joint Conference on Neural Networks, IJCNN 2007 ; Conference date: 12-08-2007 Through 17-08-2007",

}

Gupta, A & Long, LN 2007, Character recognition using spiking neural networks. in The 2007 International Joint Conference on Neural Networks, IJCNN 2007 Conference Proceedings., 4370930, IEEE International Conference on Neural Networks - Conference Proceedings, pp. 53-58, 2007 International Joint Conference on Neural Networks, IJCNN 2007, Orlando, FL, United States, 8/12/07. https://doi.org/10.1109/IJCNN.2007.4370930

TY - GEN

T1 - Character recognition using spiking neural networks

AU - Gupta, Ankur

AU - Long, Lyle N.

PY - 2007

Y1 - 2007

N2 - A spiking neural network model is used to identify characters in a character set. The network is a two layered structure consisting of integrate-and-fire and active dendrite neurons. There are both excitatory and inhibitory connections in the network. Spike time dependent plasticity (STDP) is used for training. The winner take all mechanism is enforced by the lateral inhibitory connections. It is found that most of the characters are recognized in a character set consisting of 48 characters. The network is trained successfully with increased resolution of the characters. Also, addition of uniform random noise does not decrease its recognition capability.

AB - A spiking neural network model is used to identify characters in a character set. The network is a two layered structure consisting of integrate-and-fire and active dendrite neurons. There are both excitatory and inhibitory connections in the network. Spike time dependent plasticity (STDP) is used for training. The winner take all mechanism is enforced by the lateral inhibitory connections. It is found that most of the characters are recognized in a character set consisting of 48 characters. The network is trained successfully with increased resolution of the characters. Also, addition of uniform random noise does not decrease its recognition capability.

UR - http://www.scopus.com/inward/record.url?scp=51749087481&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51749087481&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2007.4370930

DO - 10.1109/IJCNN.2007.4370930

M3 - Conference contribution

AN - SCOPUS:51749087481

SN - 142441380X

SN - 9781424413805

T3 - IEEE International Conference on Neural Networks - Conference Proceedings

SP - 53

EP - 58

BT - The 2007 International Joint Conference on Neural Networks, IJCNN 2007 Conference Proceedings

T2 - 2007 International Joint Conference on Neural Networks, IJCNN 2007

Y2 - 12 August 2007 through 17 August 2007

ER -

Character recognition using spiking neural networks

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this