Neural Connectivity Reconstruction from Calcium Imaging Signal using Random Forest with Topological Features

Wojciech M. Czarnecki, Rafal Jozefowicz
Proceedings of the Neural Connectomics Workshop at ECML 2014, PMLR 46:67-76, 2015.

Abstract

Connectomics is becoming an increasingly popular area of research. With the recent advances in optical imaging of the neural activity tens of thousands of neurons can be monitored simultaneously. In this paper we present a method of incorporating topological knowledge inside data representation for Random Forest classifier in order to reconstruct the neural connections from patterns of their activities. Proposed technique leads to the model competitive with state-of-the art methods like Deep Convolutional Neural Networks and Graph Decomposition techniques. This claim is supported by the results (5th place with 0.003 in terms of AUC ROC loss to the top contestant) obtained in the connectomics competition organized on the Kaggle platform.

Cite this Paper

BibTeX
@InProceedings{pmlr-v46-czarnecki15, title = {Neural Connectivity Reconstruction from Calcium Imaging Signal using Random Forest with Topological Features}, author = {Czarnecki, Wojciech M. and Jozefowicz, Rafal}, booktitle = {Proceedings of the Neural Connectomics Workshop at ECML 2014}, pages = {67--76}, 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/czarnecki15.pdf}, url = {https://proceedings.mlr.press/v46/czarnecki15.html}, abstract = {Connectomics is becoming an increasingly popular area of research. With the recent advances in optical imaging of the neural activity tens of thousands of neurons can be monitored simultaneously. In this paper we present a method of incorporating topological knowledge inside data representation for Random Forest classifier in order to reconstruct the neural connections from patterns of their activities. Proposed technique leads to the model competitive with state-of-the art methods like Deep Convolutional Neural Networks and Graph Decomposition techniques. This claim is supported by the results (5th place with 0.003 in terms of AUC ROC loss to the top contestant) obtained in the connectomics competition organized on the Kaggle platform.} }
Endnote
%0 Conference Paper %T Neural Connectivity Reconstruction from Calcium Imaging Signal using Random Forest with Topological Features %A Wojciech M. Czarnecki %A Rafal Jozefowicz %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-czarnecki15 %I PMLR %P 67--76 %U https://proceedings.mlr.press/v46/czarnecki15.html %V 46 %X Connectomics is becoming an increasingly popular area of research. With the recent advances in optical imaging of the neural activity tens of thousands of neurons can be monitored simultaneously. In this paper we present a method of incorporating topological knowledge inside data representation for Random Forest classifier in order to reconstruct the neural connections from patterns of their activities. Proposed technique leads to the model competitive with state-of-the art methods like Deep Convolutional Neural Networks and Graph Decomposition techniques. This claim is supported by the results (5th place with 0.003 in terms of AUC ROC loss to the top contestant) obtained in the connectomics competition organized on the Kaggle platform.
RIS
TY - CPAPER TI - Neural Connectivity Reconstruction from Calcium Imaging Signal using Random Forest with Topological Features AU - Wojciech M. Czarnecki AU - Rafal Jozefowicz 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-czarnecki15 PB - PMLR DP - Proceedings of Machine Learning Research VL - 46 SP - 67 EP - 76 L1 - http://proceedings.mlr.press/v46/czarnecki15.pdf UR - https://proceedings.mlr.press/v46/czarnecki15.html AB - Connectomics is becoming an increasingly popular area of research. With the recent advances in optical imaging of the neural activity tens of thousands of neurons can be monitored simultaneously. In this paper we present a method of incorporating topological knowledge inside data representation for Random Forest classifier in order to reconstruct the neural connections from patterns of their activities. Proposed technique leads to the model competitive with state-of-the art methods like Deep Convolutional Neural Networks and Graph Decomposition techniques. This claim is supported by the results (5th place with 0.003 in terms of AUC ROC loss to the top contestant) obtained in the connectomics competition organized on the Kaggle platform. ER -
APA
Czarnecki, W.M. & Jozefowicz, R.. (2015). Neural Connectivity Reconstruction from Calcium Imaging Signal using Random Forest with Topological Features. Proceedings of the Neural Connectomics Workshop at ECML 2014, in Proceedings of Machine Learning Research 46:67-76 Available from https://proceedings.mlr.press/v46/czarnecki15.html.

Related Material