Hierarchical mixture of classification experts uncovers interactions between brain regions

Bangpeng Yao, Dirk B. Walther, Diane M Beck, Fei Fei Li

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

Abstract

The human brain can be described as containing a number of functional regions. These regions, as well as the connections between them, play a key role in information processing in the brain. However, most existing multi-voxel pattern analysis approaches either treat multiple regions as one large uniform region or several independent regions, ignoring the connections between them. In this paper we propose to model such connections in an Hidden Conditional Random Field (HCRF) framework, where the classifier of one region of interest (ROI) makes predictions based on not only its voxels but also the predictions from ROIs that it connects to. Furthermore, we propose a structural learning method in the HCRF framework to automatically uncover the connections between ROIs. We illustrate this approach with fMRI data acquired while human subjects viewed images of different natural scene categories and show that our model can improve the top-level (the classifier combining information from all ROIs) and ROI-level prediction accuracy, as well as uncover some meaningful connections between ROIs.

Original languageEnglish (US)
Title of host publicationAdvances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference
Pages2178-2186
Number of pages9
StatePublished - Dec 1 2009
Event23rd Annual Conference on Neural Information Processing Systems, NIPS 2009 - Vancouver, BC, Canada
Duration: Dec 7 2009Dec 10 2009

Publication series

NameAdvances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference

Other

Other23rd Annual Conference on Neural Information Processing Systems, NIPS 2009
CountryCanada
CityVancouver, BC
Period12/7/0912/10/09

Fingerprint

Brain
Classifiers
Magnetic Resonance Imaging

ASJC Scopus subject areas

  • Information Systems

Cite this

Yao, B., Walther, D. B., Beck, D. M., & Li, F. F. (2009). Hierarchical mixture of classification experts uncovers interactions between brain regions. In Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference (pp. 2178-2186). (Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference).

Hierarchical mixture of classification experts uncovers interactions between brain regions. / Yao, Bangpeng; Walther, Dirk B.; Beck, Diane M; Li, Fei Fei.

Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference. 2009. p. 2178-2186 (Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference).

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

Yao, B, Walther, DB, Beck, DM & Li, FF 2009, Hierarchical mixture of classification experts uncovers interactions between brain regions. in Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference. Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference, pp. 2178-2186, 23rd Annual Conference on Neural Information Processing Systems, NIPS 2009, Vancouver, BC, Canada, 12/7/09.
Yao B, Walther DB, Beck DM, Li FF. Hierarchical mixture of classification experts uncovers interactions between brain regions. In Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference. 2009. p. 2178-2186. (Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference).
Yao, Bangpeng ; Walther, Dirk B. ; Beck, Diane M ; Li, Fei Fei. / Hierarchical mixture of classification experts uncovers interactions between brain regions. Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference. 2009. pp. 2178-2186 (Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference).
@inproceedings{0f0b81b1aa804d89aeaffbfcfe4abb49,
title = "Hierarchical mixture of classification experts uncovers interactions between brain regions",
abstract = "The human brain can be described as containing a number of functional regions. These regions, as well as the connections between them, play a key role in information processing in the brain. However, most existing multi-voxel pattern analysis approaches either treat multiple regions as one large uniform region or several independent regions, ignoring the connections between them. In this paper we propose to model such connections in an Hidden Conditional Random Field (HCRF) framework, where the classifier of one region of interest (ROI) makes predictions based on not only its voxels but also the predictions from ROIs that it connects to. Furthermore, we propose a structural learning method in the HCRF framework to automatically uncover the connections between ROIs. We illustrate this approach with fMRI data acquired while human subjects viewed images of different natural scene categories and show that our model can improve the top-level (the classifier combining information from all ROIs) and ROI-level prediction accuracy, as well as uncover some meaningful connections between ROIs.",
author = "Bangpeng Yao and Walther, {Dirk B.} and Beck, {Diane M} and Li, {Fei Fei}",
year = "2009",
month = "12",
day = "1",
language = "English (US)",
isbn = "9781615679119",
series = "Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference",
pages = "2178--2186",
booktitle = "Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference",

}

TY - GEN

T1 - Hierarchical mixture of classification experts uncovers interactions between brain regions

AU - Yao, Bangpeng

AU - Walther, Dirk B.

AU - Beck, Diane M

AU - Li, Fei Fei

PY - 2009/12/1

Y1 - 2009/12/1

N2 - The human brain can be described as containing a number of functional regions. These regions, as well as the connections between them, play a key role in information processing in the brain. However, most existing multi-voxel pattern analysis approaches either treat multiple regions as one large uniform region or several independent regions, ignoring the connections between them. In this paper we propose to model such connections in an Hidden Conditional Random Field (HCRF) framework, where the classifier of one region of interest (ROI) makes predictions based on not only its voxels but also the predictions from ROIs that it connects to. Furthermore, we propose a structural learning method in the HCRF framework to automatically uncover the connections between ROIs. We illustrate this approach with fMRI data acquired while human subjects viewed images of different natural scene categories and show that our model can improve the top-level (the classifier combining information from all ROIs) and ROI-level prediction accuracy, as well as uncover some meaningful connections between ROIs.

AB - The human brain can be described as containing a number of functional regions. These regions, as well as the connections between them, play a key role in information processing in the brain. However, most existing multi-voxel pattern analysis approaches either treat multiple regions as one large uniform region or several independent regions, ignoring the connections between them. In this paper we propose to model such connections in an Hidden Conditional Random Field (HCRF) framework, where the classifier of one region of interest (ROI) makes predictions based on not only its voxels but also the predictions from ROIs that it connects to. Furthermore, we propose a structural learning method in the HCRF framework to automatically uncover the connections between ROIs. We illustrate this approach with fMRI data acquired while human subjects viewed images of different natural scene categories and show that our model can improve the top-level (the classifier combining information from all ROIs) and ROI-level prediction accuracy, as well as uncover some meaningful connections between ROIs.

UR - http://www.scopus.com/inward/record.url?scp=84858727499&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84858727499&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84858727499

SN - 9781615679119

T3 - Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference

SP - 2178

EP - 2186

BT - Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference

ER -