Generalized correspondence-LDA models (GC-LDA) for identifying functional regions in the brain

Timothy N. Rubin, Oluwasanmi Oluseye Koyejo, Michael N. Jones, Tal Yarkoni

Research output: Contribution to journalConference article

Abstract

This paper presents Generalized Correspondence-LDA (GC-LDA), a generalization of the Correspondence-LDA model that allows for variable spatial representations to be associated with topics, and increased flexibility in terms of the strength of the correspondence between data types induced by the model. We present three variants of GC-LDA, each of which associates topics with a different spatial representation, and apply them to a corpus of neuroimaging data. In the context of this dataset, each topic corresponds to a functional brain region, where the region's spatial extent is captured by a probability distribution over neural activity, and the region's cognitive function is captured by a probability distribution over linguistic terms. We illustrate the qualitative improvements offered by GC-LDA in terms of the types of topics extracted with alternative spatial representations, as well as the model's ability to incorporate a-priori knowledge from the neuroimaging literature. We furthermore demonstrate that the novel features of GC-LDA improve predictions for missing data.

Original languageEnglish (US)
Pages (from-to)1126-1134
Number of pages9
JournalAdvances in Neural Information Processing Systems
StatePublished - Jan 1 2016
Event30th Annual Conference on Neural Information Processing Systems, NIPS 2016 - Barcelona, Spain
Duration: Dec 5 2016Dec 10 2016

Fingerprint

Brain
Neuroimaging
Probability distributions
Linguistics

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Cite this

Generalized correspondence-LDA models (GC-LDA) for identifying functional regions in the brain. / Rubin, Timothy N.; Koyejo, Oluwasanmi Oluseye; Jones, Michael N.; Yarkoni, Tal.

In: Advances in Neural Information Processing Systems, 01.01.2016, p. 1126-1134.

Research output: Contribution to journalConference article

@article{2df43950c55943128ff5da6682d8b70d,
title = "Generalized correspondence-LDA models (GC-LDA) for identifying functional regions in the brain",
abstract = "This paper presents Generalized Correspondence-LDA (GC-LDA), a generalization of the Correspondence-LDA model that allows for variable spatial representations to be associated with topics, and increased flexibility in terms of the strength of the correspondence between data types induced by the model. We present three variants of GC-LDA, each of which associates topics with a different spatial representation, and apply them to a corpus of neuroimaging data. In the context of this dataset, each topic corresponds to a functional brain region, where the region's spatial extent is captured by a probability distribution over neural activity, and the region's cognitive function is captured by a probability distribution over linguistic terms. We illustrate the qualitative improvements offered by GC-LDA in terms of the types of topics extracted with alternative spatial representations, as well as the model's ability to incorporate a-priori knowledge from the neuroimaging literature. We furthermore demonstrate that the novel features of GC-LDA improve predictions for missing data.",
author = "Rubin, {Timothy N.} and Koyejo, {Oluwasanmi Oluseye} and Jones, {Michael N.} and Tal Yarkoni",
year = "2016",
month = "1",
day = "1",
language = "English (US)",
pages = "1126--1134",
journal = "Advances in Neural Information Processing Systems",
issn = "1049-5258",

}

TY - JOUR

T1 - Generalized correspondence-LDA models (GC-LDA) for identifying functional regions in the brain

AU - Rubin, Timothy N.

AU - Koyejo, Oluwasanmi Oluseye

AU - Jones, Michael N.

AU - Yarkoni, Tal

PY - 2016/1/1

Y1 - 2016/1/1

N2 - This paper presents Generalized Correspondence-LDA (GC-LDA), a generalization of the Correspondence-LDA model that allows for variable spatial representations to be associated with topics, and increased flexibility in terms of the strength of the correspondence between data types induced by the model. We present three variants of GC-LDA, each of which associates topics with a different spatial representation, and apply them to a corpus of neuroimaging data. In the context of this dataset, each topic corresponds to a functional brain region, where the region's spatial extent is captured by a probability distribution over neural activity, and the region's cognitive function is captured by a probability distribution over linguistic terms. We illustrate the qualitative improvements offered by GC-LDA in terms of the types of topics extracted with alternative spatial representations, as well as the model's ability to incorporate a-priori knowledge from the neuroimaging literature. We furthermore demonstrate that the novel features of GC-LDA improve predictions for missing data.

AB - This paper presents Generalized Correspondence-LDA (GC-LDA), a generalization of the Correspondence-LDA model that allows for variable spatial representations to be associated with topics, and increased flexibility in terms of the strength of the correspondence between data types induced by the model. We present three variants of GC-LDA, each of which associates topics with a different spatial representation, and apply them to a corpus of neuroimaging data. In the context of this dataset, each topic corresponds to a functional brain region, where the region's spatial extent is captured by a probability distribution over neural activity, and the region's cognitive function is captured by a probability distribution over linguistic terms. We illustrate the qualitative improvements offered by GC-LDA in terms of the types of topics extracted with alternative spatial representations, as well as the model's ability to incorporate a-priori knowledge from the neuroimaging literature. We furthermore demonstrate that the novel features of GC-LDA improve predictions for missing data.

UR - http://www.scopus.com/inward/record.url?scp=85019217807&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85019217807&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85019217807

SP - 1126

EP - 1134

JO - Advances in Neural Information Processing Systems

JF - Advances in Neural Information Processing Systems

SN - 1049-5258

ER -