Introduction to machine learning for brain imaging

Steven Lemm, Benjamin Blankertz, Thorsten Dickhaus, Klaus Muller

Research output: Contribution to journalArticle

341 Citations (Scopus)

Abstract

Machine learning and pattern recognition algorithms have in the past years developed to become a working horse in brain imaging and the computational neurosciences, as they are instrumental for mining vast amounts of neural data of ever increasing measurement precision and detecting minuscule signals from an overwhelming noise floor. They provide the means to decode and characterize task relevant brain states and to distinguish them from non-informative brain signals. While undoubtedly this machinery has helped to gain novel biological insights, it also holds the danger of potential unintentional abuse. Ideally machine learning techniques should be usable for any non-expert, however, unfortunately they are typically not. Overfitting and other pitfalls may occur and lead to spurious and nonsensical interpretation. The goal of this review is therefore to provide an accessible and clear introduction to the strengths and also the inherent dangers of machine learning usage in the neurosciences.

Original languageEnglish
Pages (from-to)387-399
Number of pages13
JournalNeuroImage
Volume56
Issue number2
DOIs
Publication statusPublished - 2011 May 15
Externally publishedYes

Fingerprint

Neuroimaging
Neurosciences
Brain
Horses
Machine Learning

Keywords

  • Cross validation
  • Machine learning
  • Model selection
  • Pattern recognition

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Neurology

Cite this

Lemm, S., Blankertz, B., Dickhaus, T., & Muller, K. (2011). Introduction to machine learning for brain imaging. NeuroImage, 56(2), 387-399. https://doi.org/10.1016/j.neuroimage.2010.11.004

Introduction to machine learning for brain imaging. / Lemm, Steven; Blankertz, Benjamin; Dickhaus, Thorsten; Muller, Klaus.

In: NeuroImage, Vol. 56, No. 2, 15.05.2011, p. 387-399.

Research output: Contribution to journalArticle

Lemm, S, Blankertz, B, Dickhaus, T & Muller, K 2011, 'Introduction to machine learning for brain imaging', NeuroImage, vol. 56, no. 2, pp. 387-399. https://doi.org/10.1016/j.neuroimage.2010.11.004
Lemm S, Blankertz B, Dickhaus T, Muller K. Introduction to machine learning for brain imaging. NeuroImage. 2011 May 15;56(2):387-399. https://doi.org/10.1016/j.neuroimage.2010.11.004
Lemm, Steven ; Blankertz, Benjamin ; Dickhaus, Thorsten ; Muller, Klaus. / Introduction to machine learning for brain imaging. In: NeuroImage. 2011 ; Vol. 56, No. 2. pp. 387-399.
@article{7632c4305e28410185cd459e22566364,
title = "Introduction to machine learning for brain imaging",
abstract = "Machine learning and pattern recognition algorithms have in the past years developed to become a working horse in brain imaging and the computational neurosciences, as they are instrumental for mining vast amounts of neural data of ever increasing measurement precision and detecting minuscule signals from an overwhelming noise floor. They provide the means to decode and characterize task relevant brain states and to distinguish them from non-informative brain signals. While undoubtedly this machinery has helped to gain novel biological insights, it also holds the danger of potential unintentional abuse. Ideally machine learning techniques should be usable for any non-expert, however, unfortunately they are typically not. Overfitting and other pitfalls may occur and lead to spurious and nonsensical interpretation. The goal of this review is therefore to provide an accessible and clear introduction to the strengths and also the inherent dangers of machine learning usage in the neurosciences.",
keywords = "Cross validation, Machine learning, Model selection, Pattern recognition",
author = "Steven Lemm and Benjamin Blankertz and Thorsten Dickhaus and Klaus Muller",
year = "2011",
month = "5",
day = "15",
doi = "10.1016/j.neuroimage.2010.11.004",
language = "English",
volume = "56",
pages = "387--399",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",
number = "2",

}

TY - JOUR

T1 - Introduction to machine learning for brain imaging

AU - Lemm, Steven

AU - Blankertz, Benjamin

AU - Dickhaus, Thorsten

AU - Muller, Klaus

PY - 2011/5/15

Y1 - 2011/5/15

N2 - Machine learning and pattern recognition algorithms have in the past years developed to become a working horse in brain imaging and the computational neurosciences, as they are instrumental for mining vast amounts of neural data of ever increasing measurement precision and detecting minuscule signals from an overwhelming noise floor. They provide the means to decode and characterize task relevant brain states and to distinguish them from non-informative brain signals. While undoubtedly this machinery has helped to gain novel biological insights, it also holds the danger of potential unintentional abuse. Ideally machine learning techniques should be usable for any non-expert, however, unfortunately they are typically not. Overfitting and other pitfalls may occur and lead to spurious and nonsensical interpretation. The goal of this review is therefore to provide an accessible and clear introduction to the strengths and also the inherent dangers of machine learning usage in the neurosciences.

AB - Machine learning and pattern recognition algorithms have in the past years developed to become a working horse in brain imaging and the computational neurosciences, as they are instrumental for mining vast amounts of neural data of ever increasing measurement precision and detecting minuscule signals from an overwhelming noise floor. They provide the means to decode and characterize task relevant brain states and to distinguish them from non-informative brain signals. While undoubtedly this machinery has helped to gain novel biological insights, it also holds the danger of potential unintentional abuse. Ideally machine learning techniques should be usable for any non-expert, however, unfortunately they are typically not. Overfitting and other pitfalls may occur and lead to spurious and nonsensical interpretation. The goal of this review is therefore to provide an accessible and clear introduction to the strengths and also the inherent dangers of machine learning usage in the neurosciences.

KW - Cross validation

KW - Machine learning

KW - Model selection

KW - Pattern recognition

UR - http://www.scopus.com/inward/record.url?scp=79954990666&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79954990666&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2010.11.004

DO - 10.1016/j.neuroimage.2010.11.004

M3 - Article

C2 - 21172442

AN - SCOPUS:79954990666

VL - 56

SP - 387

EP - 399

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

IS - 2

ER -