Regularized hyperalignment of multi-set fMRI data

Hao Xu; Alexander Lorbert; Peter J. Ramadge; J. Swaroop Guntupalli; James V. Haxby

doi:10.1109/SSP.2012.6319668

Regularized hyperalignment of multi-set fMRI data

Hao Xu, Alexander Lorbert, Peter J. Ramadge, J. Swaroop Guntupalli, James V. Haxby

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

32 Scopus citations

Abstract

Inter-subject correspondence is an important aspect of multi-subject fMRI studies. Recently, a new approach, called hyperalignment, has shown very promising results in fMRI functional alignment. Hyperalignment is based on Procrustean rotations and is connected, mathematically, to canonical correlation analysis. We review the core details of each approach, relate them through an SVD analysis, and indicate why they can yield different levels of performance. We then examine the effectiveness of regularization in mediating between the extremes of these methods. An inter-subject classification experiment based on functional aligned fMRI datasets illustrates the resulting improved performance.

Original language	English (US)
Title of host publication	2012 IEEE Statistical Signal Processing Workshop, SSP 2012
Pages	229-232
Number of pages	4
DOIs	https://doi.org/10.1109/SSP.2012.6319668
State	Published - 2012
Event	2012 IEEE Statistical Signal Processing Workshop, SSP 2012 - Ann Arbor, MI, United States Duration: Aug 5 2012 → Aug 8 2012

Publication series

Name	2012 IEEE Statistical Signal Processing Workshop, SSP 2012

Other

Other	2012 IEEE Statistical Signal Processing Workshop, SSP 2012
Country/Territory	United States
City	Ann Arbor, MI
Period	8/5/12 → 8/8/12

All Science Journal Classification (ASJC) codes

Signal Processing

Keywords

Alignment
Canonical Correlation
Procrustes Problems
fMRI

Access to Document

10.1109/SSP.2012.6319668

Cite this

@inproceedings{274b42e3a0634d37a99dfd4e7ecee32a,

title = "Regularized hyperalignment of multi-set fMRI data",

abstract = "Inter-subject correspondence is an important aspect of multi-subject fMRI studies. Recently, a new approach, called hyperalignment, has shown very promising results in fMRI functional alignment. Hyperalignment is based on Procrustean rotations and is connected, mathematically, to canonical correlation analysis. We review the core details of each approach, relate them through an SVD analysis, and indicate why they can yield different levels of performance. We then examine the effectiveness of regularization in mediating between the extremes of these methods. An inter-subject classification experiment based on functional aligned fMRI datasets illustrates the resulting improved performance.",

keywords = "Alignment, Canonical Correlation, Procrustes Problems, fMRI",

author = "Hao Xu and Alexander Lorbert and Ramadge, {Peter J.} and Guntupalli, {J. Swaroop} and Haxby, {James V.}",

year = "2012",

doi = "10.1109/SSP.2012.6319668",

language = "English (US)",

isbn = "9781467301831",

series = "2012 IEEE Statistical Signal Processing Workshop, SSP 2012",

pages = "229--232",

booktitle = "2012 IEEE Statistical Signal Processing Workshop, SSP 2012",

note = "2012 IEEE Statistical Signal Processing Workshop, SSP 2012 ; Conference date: 05-08-2012 Through 08-08-2012",

}

Xu, H, Lorbert, A, Ramadge, PJ, Guntupalli, JS & Haxby, JV 2012, Regularized hyperalignment of multi-set fMRI data. in 2012 IEEE Statistical Signal Processing Workshop, SSP 2012., 6319668, 2012 IEEE Statistical Signal Processing Workshop, SSP 2012, pp. 229-232, 2012 IEEE Statistical Signal Processing Workshop, SSP 2012, Ann Arbor, MI, United States, 8/5/12. https://doi.org/10.1109/SSP.2012.6319668

TY - GEN

T1 - Regularized hyperalignment of multi-set fMRI data

AU - Xu, Hao

AU - Lorbert, Alexander

AU - Ramadge, Peter J.

AU - Guntupalli, J. Swaroop

AU - Haxby, James V.

PY - 2012

Y1 - 2012

N2 - Inter-subject correspondence is an important aspect of multi-subject fMRI studies. Recently, a new approach, called hyperalignment, has shown very promising results in fMRI functional alignment. Hyperalignment is based on Procrustean rotations and is connected, mathematically, to canonical correlation analysis. We review the core details of each approach, relate them through an SVD analysis, and indicate why they can yield different levels of performance. We then examine the effectiveness of regularization in mediating between the extremes of these methods. An inter-subject classification experiment based on functional aligned fMRI datasets illustrates the resulting improved performance.

AB - Inter-subject correspondence is an important aspect of multi-subject fMRI studies. Recently, a new approach, called hyperalignment, has shown very promising results in fMRI functional alignment. Hyperalignment is based on Procrustean rotations and is connected, mathematically, to canonical correlation analysis. We review the core details of each approach, relate them through an SVD analysis, and indicate why they can yield different levels of performance. We then examine the effectiveness of regularization in mediating between the extremes of these methods. An inter-subject classification experiment based on functional aligned fMRI datasets illustrates the resulting improved performance.

KW - Alignment

KW - Canonical Correlation

KW - Procrustes Problems

KW - fMRI

UR - http://www.scopus.com/inward/record.url?scp=84868247083&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84868247083&partnerID=8YFLogxK

U2 - 10.1109/SSP.2012.6319668

DO - 10.1109/SSP.2012.6319668

M3 - Conference contribution

AN - SCOPUS:84868247083

SN - 9781467301831

T3 - 2012 IEEE Statistical Signal Processing Workshop, SSP 2012

SP - 229

EP - 232

BT - 2012 IEEE Statistical Signal Processing Workshop, SSP 2012

T2 - 2012 IEEE Statistical Signal Processing Workshop, SSP 2012

Y2 - 5 August 2012 through 8 August 2012

ER -

Regularized hyperalignment of multi-set fMRI data

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this