Simple Connectome Inference from Partial Correlation Statistics in Calcium Imaging

Antonio Sutera, Arnaud Joly, Vincent Francois-Lavet, Aaron Qiu, Gilles Louppe, Damien Ernst, Pierre Geurts
Proceedings of the Neural Connectomics Workshop at ECML 2014, PMLR 46:23-35, 2015.

Abstract

In this work, we propose a simple yet effective solution to the problem of connectome inference in calcium imaging data. The proposed algorithm consists of two steps. First, processing the raw signals to detect neural peak activities. Second, inferring the degree of association between neurons from partial correlation statistics. This paper summarises the methodology that led us to win the Connectomics Challenge, proposes a simplified version of our method, and finally compares our results with respect to other inference methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v46-sutera15, title = {Simple Connectome Inference from Partial Correlation Statistics in Calcium Imaging}, author = {Sutera, Antonio and Joly, Arnaud and Francois-Lavet, Vincent and Qiu, Aaron and Louppe, Gilles and Ernst, Damien and Geurts, Pierre}, booktitle = {Proceedings of the Neural Connectomics Workshop at ECML 2014}, pages = {23--35}, year = {2015}, editor = {Battaglia, Demian and Guyon, Isabelle and Lemaire, Vincent and Soriano, Jordi}, volume = {46}, series = {Proceedings of Machine Learning Research}, month = {15 Sep}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v46/sutera15.pdf}, url = {https://proceedings.mlr.press/v46/sutera15.html}, abstract = {In this work, we propose a simple yet effective solution to the problem of connectome inference in calcium imaging data. The proposed algorithm consists of two steps. First, processing the raw signals to detect neural peak activities. Second, inferring the degree of association between neurons from partial correlation statistics. This paper summarises the methodology that led us to win the Connectomics Challenge, proposes a simplified version of our method, and finally compares our results with respect to other inference methods.} }
Endnote
%0 Conference Paper %T Simple Connectome Inference from Partial Correlation Statistics in Calcium Imaging %A Antonio Sutera %A Arnaud Joly %A Vincent Francois-Lavet %A Aaron Qiu %A Gilles Louppe %A Damien Ernst %A Pierre Geurts %B Proceedings of the Neural Connectomics Workshop at ECML 2014 %C Proceedings of Machine Learning Research %D 2015 %E Demian Battaglia %E Isabelle Guyon %E Vincent Lemaire %E Jordi Soriano %F pmlr-v46-sutera15 %I PMLR %P 23--35 %U https://proceedings.mlr.press/v46/sutera15.html %V 46 %X In this work, we propose a simple yet effective solution to the problem of connectome inference in calcium imaging data. The proposed algorithm consists of two steps. First, processing the raw signals to detect neural peak activities. Second, inferring the degree of association between neurons from partial correlation statistics. This paper summarises the methodology that led us to win the Connectomics Challenge, proposes a simplified version of our method, and finally compares our results with respect to other inference methods.
RIS
TY - CPAPER TI - Simple Connectome Inference from Partial Correlation Statistics in Calcium Imaging AU - Antonio Sutera AU - Arnaud Joly AU - Vincent Francois-Lavet AU - Aaron Qiu AU - Gilles Louppe AU - Damien Ernst AU - Pierre Geurts BT - Proceedings of the Neural Connectomics Workshop at ECML 2014 DA - 2015/10/21 ED - Demian Battaglia ED - Isabelle Guyon ED - Vincent Lemaire ED - Jordi Soriano ID - pmlr-v46-sutera15 PB - PMLR DP - Proceedings of Machine Learning Research VL - 46 SP - 23 EP - 35 L1 - http://proceedings.mlr.press/v46/sutera15.pdf UR - https://proceedings.mlr.press/v46/sutera15.html AB - In this work, we propose a simple yet effective solution to the problem of connectome inference in calcium imaging data. The proposed algorithm consists of two steps. First, processing the raw signals to detect neural peak activities. Second, inferring the degree of association between neurons from partial correlation statistics. This paper summarises the methodology that led us to win the Connectomics Challenge, proposes a simplified version of our method, and finally compares our results with respect to other inference methods. ER -
APA
Sutera, A., Joly, A., Francois-Lavet, V., Qiu, A., Louppe, G., Ernst, D. & Geurts, P.. (2015). Simple Connectome Inference from Partial Correlation Statistics in Calcium Imaging. Proceedings of the Neural Connectomics Workshop at ECML 2014, in Proceedings of Machine Learning Research 46:23-35 Available from https://proceedings.mlr.press/v46/sutera15.html.

Related Material