Fast algorithm for neural network reconstruction

Sean Bittner, Siheng Chen, Jelena Kovacevic

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

Abstract

We propose an efficient and accurate way of predicting the connectivity of neural networks in the brain represented by simulated calcium fluorescence data. Classical methods to neural network reconstruction compute a connectivity matrix whose entries are pairwise likelihoods of directed excitatory connections based on time-series signals of each pair of neurons. Our method uses only a fraction of this computation to achieve equal or better performance. The proposed method is based on matrix completion and a local thresholding technique. By computing a subset of the total entries in the connectivity matrix, we use matrix completion to determine the rest of the connection likelihoods, and apply a local threshold to identify which directed connections exist in the underlying network. We validate the proposed method on a simulated calcium fluorescence dataset. The proposed method outperforms the classical one with 20% of the computation.

Original languageEnglish (US)
Title of host publication2015 IEEE 12th International Symposium on Biomedical Imaging, ISBI 2015
PublisherIEEE Computer Society
Pages866-869
Number of pages4
Volume2015-July
ISBN (Electronic)9781479923748
DOIs
StatePublished - Jan 1 2015
Event12th IEEE International Symposium on Biomedical Imaging, ISBI 2015 - Brooklyn, United States
Duration: Apr 16 2015Apr 19 2015

Other

Other12th IEEE International Symposium on Biomedical Imaging, ISBI 2015
CountryUnited States
CityBrooklyn
Period4/16/154/19/15

Fingerprint

Neural networks
Calcium
Fluorescence
Neurons
Time series
Brain

Keywords

  • connectivity analysis
  • machine learning
  • nerves

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Bittner, S., Chen, S., & Kovacevic, J. (2015). Fast algorithm for neural network reconstruction. In 2015 IEEE 12th International Symposium on Biomedical Imaging, ISBI 2015 (Vol. 2015-July, pp. 866-869). [7164008] IEEE Computer Society. https://doi.org/10.1109/ISBI.2015.7164008

Fast algorithm for neural network reconstruction. / Bittner, Sean; Chen, Siheng; Kovacevic, Jelena.

2015 IEEE 12th International Symposium on Biomedical Imaging, ISBI 2015. Vol. 2015-July IEEE Computer Society, 2015. p. 866-869 7164008.

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

Bittner, S, Chen, S & Kovacevic, J 2015, Fast algorithm for neural network reconstruction. in 2015 IEEE 12th International Symposium on Biomedical Imaging, ISBI 2015. vol. 2015-July, 7164008, IEEE Computer Society, pp. 866-869, 12th IEEE International Symposium on Biomedical Imaging, ISBI 2015, Brooklyn, United States, 4/16/15. https://doi.org/10.1109/ISBI.2015.7164008
Bittner S, Chen S, Kovacevic J. Fast algorithm for neural network reconstruction. In 2015 IEEE 12th International Symposium on Biomedical Imaging, ISBI 2015. Vol. 2015-July. IEEE Computer Society. 2015. p. 866-869. 7164008 https://doi.org/10.1109/ISBI.2015.7164008
Bittner, Sean ; Chen, Siheng ; Kovacevic, Jelena. / Fast algorithm for neural network reconstruction. 2015 IEEE 12th International Symposium on Biomedical Imaging, ISBI 2015. Vol. 2015-July IEEE Computer Society, 2015. pp. 866-869
@inproceedings{8308850deef34324a903df5cf00548ff,
title = "Fast algorithm for neural network reconstruction",
abstract = "We propose an efficient and accurate way of predicting the connectivity of neural networks in the brain represented by simulated calcium fluorescence data. Classical methods to neural network reconstruction compute a connectivity matrix whose entries are pairwise likelihoods of directed excitatory connections based on time-series signals of each pair of neurons. Our method uses only a fraction of this computation to achieve equal or better performance. The proposed method is based on matrix completion and a local thresholding technique. By computing a subset of the total entries in the connectivity matrix, we use matrix completion to determine the rest of the connection likelihoods, and apply a local threshold to identify which directed connections exist in the underlying network. We validate the proposed method on a simulated calcium fluorescence dataset. The proposed method outperforms the classical one with 20{\%} of the computation.",
keywords = "connectivity analysis, machine learning, nerves",
author = "Sean Bittner and Siheng Chen and Jelena Kovacevic",
year = "2015",
month = "1",
day = "1",
doi = "10.1109/ISBI.2015.7164008",
language = "English (US)",
volume = "2015-July",
pages = "866--869",
booktitle = "2015 IEEE 12th International Symposium on Biomedical Imaging, ISBI 2015",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Fast algorithm for neural network reconstruction

AU - Bittner, Sean

AU - Chen, Siheng

AU - Kovacevic, Jelena

PY - 2015/1/1

Y1 - 2015/1/1

N2 - We propose an efficient and accurate way of predicting the connectivity of neural networks in the brain represented by simulated calcium fluorescence data. Classical methods to neural network reconstruction compute a connectivity matrix whose entries are pairwise likelihoods of directed excitatory connections based on time-series signals of each pair of neurons. Our method uses only a fraction of this computation to achieve equal or better performance. The proposed method is based on matrix completion and a local thresholding technique. By computing a subset of the total entries in the connectivity matrix, we use matrix completion to determine the rest of the connection likelihoods, and apply a local threshold to identify which directed connections exist in the underlying network. We validate the proposed method on a simulated calcium fluorescence dataset. The proposed method outperforms the classical one with 20% of the computation.

AB - We propose an efficient and accurate way of predicting the connectivity of neural networks in the brain represented by simulated calcium fluorescence data. Classical methods to neural network reconstruction compute a connectivity matrix whose entries are pairwise likelihoods of directed excitatory connections based on time-series signals of each pair of neurons. Our method uses only a fraction of this computation to achieve equal or better performance. The proposed method is based on matrix completion and a local thresholding technique. By computing a subset of the total entries in the connectivity matrix, we use matrix completion to determine the rest of the connection likelihoods, and apply a local threshold to identify which directed connections exist in the underlying network. We validate the proposed method on a simulated calcium fluorescence dataset. The proposed method outperforms the classical one with 20% of the computation.

KW - connectivity analysis

KW - machine learning

KW - nerves

UR - http://www.scopus.com/inward/record.url?scp=84944323017&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84944323017&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2015.7164008

DO - 10.1109/ISBI.2015.7164008

M3 - Conference contribution

VL - 2015-July

SP - 866

EP - 869

BT - 2015 IEEE 12th International Symposium on Biomedical Imaging, ISBI 2015

PB - IEEE Computer Society

ER -