An associative memory readout in ESN for neural action potential detection

Nicolas J. Dedual, Mustafa C. Ozturk, Justin C. Sanchez, José C. Principe

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

This paper describes how Echo State Networks (ESN) can be used in conjunction with Minimum Average Correlation Energy (MACE) filters in order to create a system that can identify spikes in neural recordings. Various experiments using real-world data were used to compare the performance of the ESN-MACE against threshold and matched filter detectors to ascertain the capabilities of such a system in detecting neural action potentials. The experiments demonstrate that the ESN-MACE can correctly detect spikes with lower false alarm rates than established detection techniques since it captures the inherent variability and the covariance information in spike shapes by training.

Original languageEnglish
Title of host publicationIEEE International Conference on Neural Networks - Conference Proceedings
Pages2295-2299
Number of pages5
DOIs
StatePublished - Dec 1 2007
Externally publishedYes
Event2007 International Joint Conference on Neural Networks, IJCNN 2007 - Orlando, FL, United States
Duration: Aug 12 2007Aug 17 2007

Other

Other2007 International Joint Conference on Neural Networks, IJCNN 2007
CountryUnited States
CityOrlando, FL
Period8/12/078/17/07

Fingerprint

Data storage equipment
Matched filters
Experiments
Detectors

ASJC Scopus subject areas

  • Software

Cite this

Dedual, N. J., Ozturk, M. C., Sanchez, J. C., & Principe, J. C. (2007). An associative memory readout in ESN for neural action potential detection. In IEEE International Conference on Neural Networks - Conference Proceedings (pp. 2295-2299). [4371316] https://doi.org/10.1109/IJCNN.2007.4371316

An associative memory readout in ESN for neural action potential detection. / Dedual, Nicolas J.; Ozturk, Mustafa C.; Sanchez, Justin C.; Principe, José C.

IEEE International Conference on Neural Networks - Conference Proceedings. 2007. p. 2295-2299 4371316.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Dedual, NJ, Ozturk, MC, Sanchez, JC & Principe, JC 2007, An associative memory readout in ESN for neural action potential detection. in IEEE International Conference on Neural Networks - Conference Proceedings., 4371316, pp. 2295-2299, 2007 International Joint Conference on Neural Networks, IJCNN 2007, Orlando, FL, United States, 8/12/07. https://doi.org/10.1109/IJCNN.2007.4371316
Dedual NJ, Ozturk MC, Sanchez JC, Principe JC. An associative memory readout in ESN for neural action potential detection. In IEEE International Conference on Neural Networks - Conference Proceedings. 2007. p. 2295-2299. 4371316 https://doi.org/10.1109/IJCNN.2007.4371316
Dedual, Nicolas J. ; Ozturk, Mustafa C. ; Sanchez, Justin C. ; Principe, José C. / An associative memory readout in ESN for neural action potential detection. IEEE International Conference on Neural Networks - Conference Proceedings. 2007. pp. 2295-2299
@inproceedings{2c1c84dd81ff4604ba4430646667a7c2,
title = "An associative memory readout in ESN for neural action potential detection",
abstract = "This paper describes how Echo State Networks (ESN) can be used in conjunction with Minimum Average Correlation Energy (MACE) filters in order to create a system that can identify spikes in neural recordings. Various experiments using real-world data were used to compare the performance of the ESN-MACE against threshold and matched filter detectors to ascertain the capabilities of such a system in detecting neural action potentials. The experiments demonstrate that the ESN-MACE can correctly detect spikes with lower false alarm rates than established detection techniques since it captures the inherent variability and the covariance information in spike shapes by training.",
author = "Dedual, {Nicolas J.} and Ozturk, {Mustafa C.} and Sanchez, {Justin C.} and Principe, {Jos{\'e} C.}",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/IJCNN.2007.4371316",
language = "English",
isbn = "142441380X",
pages = "2295--2299",
booktitle = "IEEE International Conference on Neural Networks - Conference Proceedings",

}

TY - GEN

T1 - An associative memory readout in ESN for neural action potential detection

AU - Dedual, Nicolas J.

AU - Ozturk, Mustafa C.

AU - Sanchez, Justin C.

AU - Principe, José C.

PY - 2007/12/1

Y1 - 2007/12/1

N2 - This paper describes how Echo State Networks (ESN) can be used in conjunction with Minimum Average Correlation Energy (MACE) filters in order to create a system that can identify spikes in neural recordings. Various experiments using real-world data were used to compare the performance of the ESN-MACE against threshold and matched filter detectors to ascertain the capabilities of such a system in detecting neural action potentials. The experiments demonstrate that the ESN-MACE can correctly detect spikes with lower false alarm rates than established detection techniques since it captures the inherent variability and the covariance information in spike shapes by training.

AB - This paper describes how Echo State Networks (ESN) can be used in conjunction with Minimum Average Correlation Energy (MACE) filters in order to create a system that can identify spikes in neural recordings. Various experiments using real-world data were used to compare the performance of the ESN-MACE against threshold and matched filter detectors to ascertain the capabilities of such a system in detecting neural action potentials. The experiments demonstrate that the ESN-MACE can correctly detect spikes with lower false alarm rates than established detection techniques since it captures the inherent variability and the covariance information in spike shapes by training.

UR - http://www.scopus.com/inward/record.url?scp=51749102148&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51749102148&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2007.4371316

DO - 10.1109/IJCNN.2007.4371316

M3 - Conference contribution

SN - 142441380X

SN - 9781424413805

SP - 2295

EP - 2299

BT - IEEE International Conference on Neural Networks - Conference Proceedings

ER -