Reconstruction of Excitatory Neuronal Connectivity via Metric Score Pooling and Regularization

Chenyang Tao, Wei Lin, Jianfeng Feng
Proceedings of the Neural Connectomics Workshop at ECML 2014, PMLR 46:57-66, 2015.

Abstract

Unravelling the causal link of neuronal pairs has considerable impacts in neuroscience, yet it still remains a major challenge. Recent investigations in the literature show that the Generalized Transfer Entropy (GTE), derived from information theory, has a great capability of reconstructing the underlying connectomics. In this work, we first generalize the GTE to a measure called Csiszar’s Transfer Entropy (CTE). With a proper choice of the convex function, the CTE outperforms the GTE in connectomic reconstruction, especially in the synchronized bursting regime where the GTE was reported to have poor sensitivity. Akin to the ensemble learning approach, we then pool various measures to achieve cutting edge neuronal network connectomic reconstruction performance. As a final step emphasize the importance of introducing regularization schemes in the network reconstruction.

Cite this Paper

BibTeX
@InProceedings{pmlr-v46-tao15, title = {Reconstruction of Excitatory Neuronal Connectivity via Metric Score Pooling and Regularization}, author = {Tao, Chenyang and Lin, Wei and Feng, Jianfeng}, booktitle = {Proceedings of the Neural Connectomics Workshop at ECML 2014}, pages = {57--66}, 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/tao15.pdf}, url = {https://proceedings.mlr.press/v46/tao15.html}, abstract = {Unravelling the causal link of neuronal pairs has considerable impacts in neuroscience, yet it still remains a major challenge. Recent investigations in the literature show that the Generalized Transfer Entropy (GTE), derived from information theory, has a great capability of reconstructing the underlying connectomics. In this work, we first generalize the GTE to a measure called Csiszar’s Transfer Entropy (CTE). With a proper choice of the convex function, the CTE outperforms the GTE in connectomic reconstruction, especially in the synchronized bursting regime where the GTE was reported to have poor sensitivity. Akin to the ensemble learning approach, we then pool various measures to achieve cutting edge neuronal network connectomic reconstruction performance. As a final step emphasize the importance of introducing regularization schemes in the network reconstruction.} }
Endnote
%0 Conference Paper %T Reconstruction of Excitatory Neuronal Connectivity via Metric Score Pooling and Regularization %A Chenyang Tao %A Wei Lin %A Jianfeng Feng %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-tao15 %I PMLR %P 57--66 %U https://proceedings.mlr.press/v46/tao15.html %V 46 %X Unravelling the causal link of neuronal pairs has considerable impacts in neuroscience, yet it still remains a major challenge. Recent investigations in the literature show that the Generalized Transfer Entropy (GTE), derived from information theory, has a great capability of reconstructing the underlying connectomics. In this work, we first generalize the GTE to a measure called Csiszar’s Transfer Entropy (CTE). With a proper choice of the convex function, the CTE outperforms the GTE in connectomic reconstruction, especially in the synchronized bursting regime where the GTE was reported to have poor sensitivity. Akin to the ensemble learning approach, we then pool various measures to achieve cutting edge neuronal network connectomic reconstruction performance. As a final step emphasize the importance of introducing regularization schemes in the network reconstruction.
RIS
TY - CPAPER TI - Reconstruction of Excitatory Neuronal Connectivity via Metric Score Pooling and Regularization AU - Chenyang Tao AU - Wei Lin AU - Jianfeng Feng 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-tao15 PB - PMLR DP - Proceedings of Machine Learning Research VL - 46 SP - 57 EP - 66 L1 - http://proceedings.mlr.press/v46/tao15.pdf UR - https://proceedings.mlr.press/v46/tao15.html AB - Unravelling the causal link of neuronal pairs has considerable impacts in neuroscience, yet it still remains a major challenge. Recent investigations in the literature show that the Generalized Transfer Entropy (GTE), derived from information theory, has a great capability of reconstructing the underlying connectomics. In this work, we first generalize the GTE to a measure called Csiszar’s Transfer Entropy (CTE). With a proper choice of the convex function, the CTE outperforms the GTE in connectomic reconstruction, especially in the synchronized bursting regime where the GTE was reported to have poor sensitivity. Akin to the ensemble learning approach, we then pool various measures to achieve cutting edge neuronal network connectomic reconstruction performance. As a final step emphasize the importance of introducing regularization schemes in the network reconstruction. ER -
APA
Tao, C., Lin, W. & Feng, J.. (2015). Reconstruction of Excitatory Neuronal Connectivity via Metric Score Pooling and Regularization. Proceedings of the Neural Connectomics Workshop at ECML 2014, in Proceedings of Machine Learning Research 46:57-66 Available from https://proceedings.mlr.press/v46/tao15.html.

Related Material