Reference : Simple connectome inference from partial correlation statistics in calcium imaging
Scientific congresses and symposiums : Paper published in a book
Engineering, computing & technology : Computer science
http://hdl.handle.net/2268/169767
Simple connectome inference from partial correlation statistics in calcium imaging
English
Sutera, Antonio mailto [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Algorith. des syst. en interaction avec le monde physique >]
Joly, Arnaud mailto [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
François-Lavet, Vincent mailto [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Smart grids >]
Qiu, Zixiao mailto [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Smart grids >]
Louppe, Gilles mailto [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
Ernst, Damien mailto [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Smart grids >]
Geurts, Pierre mailto [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Algorith. des syst. en interaction avec le monde physique >]
Jun-2014
Proceedings of Connectomics 2014 (ECML 2014)
Yes
International
7th European machine learning and data mining conference (ECML-PKDD 2014)
Du 15 septembre au 19 septembre 2014
Nancy
France
[en] Connectomics ; Network inference ; Partial correlation
[en] 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.
Researchers ; Professionals
http://hdl.handle.net/2268/169767
also: http://hdl.handle.net/2268/172139 ; http://hdl.handle.net/2268/176594
http://arxiv.org/abs/1406.7865
http://github.com/asutera/kaggle-connectomics
This is the paper that explains the methodology we developed for winning the Connectomics challenge for which the goal was to infer from observed data the wiring diagram from the brain. 144 teams were participating to this challenge.

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
sutera14.pdfAuthor postprint735.88 kBView/Open

Additional material(s):

File Commentary Size Access
Open access
slides.pdfSlides / Transparents814.94 kBView/Open
Open access
poster.pdf313.58 kBView/Open
Open access
spotlight.pdf61.96 kBView/Open

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.