Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.
Alexandre Gramfort
http://alexandre.gramfort.net
http://scikit-learn.org
“Lire dans les pensées avec Scikit-Learn”
“Mind R...
Alexandre Gramfort Mind Reading with the Scikit-Learn
Basics of Functional MRI (fMRI)
2
Oxy. Hb
Deoxy. Hb
Neurons
3D volum...
courtesy of GaelVaroquauxhttp://www.youtube.com/watch?v=uhCF-zlk0jY
Alexandre Gramfort Mind Reading with the Scikit-Learn
Learning from fMRI
4
Image,
sound, task
fMRI volumes
Challenge: Lear...
Alexandre Gramfort Mind Reading with the Scikit-Learn
Result from Miyawaki et al. Neuron 2008
5
http://www.youtube.com/wat...
Alexandre Gramfort Mind Reading with the Scikit-Learn
Result from Miyawaki et al. Neuron 2008
6
• Some details about the d...
Alexandre Gramfort Mind Reading with the Scikit-Learn
Result from Nishimoto et al. 2011
7
http://www.youtube.com/watch?v=n...
Alexandre Gramfort Mind Reading with the Scikit-Learn
Result from Nishimoto et al. 2011
8
• Some details about the data:
•...
Alexandre Gramfort Mind Reading with the Scikit-Learn
Classification example with fMRI
9
!!"#$%&'()*+,-#./
0123(%45678*####...
Demo on
Haxby et al. Science 2001
Challenge: Predict the object category viewed
Sample stimuli:
Face House Chair Shoe
Alexandre Gramfort Mind Reading with the Scikit-Learn
Miyawaki et al. 2008 with Scikit-Learn
11
< 250 Lines of codes
Alexandre Gramfort
alexandre.gramfort@telecom-paristech.fr
http://alexandre.gramfort.net
http://www.github.com/agramfort
@...
Upcoming SlideShare
Loading in …5
×

Paris machine learning meetup 17 Sept. 2013

1,827 views

Published on

Brief intro to machine learning for mining functional MRI data

Published in: Technology, Education
  • Be the first to comment

  • Be the first to like this

Paris machine learning meetup 17 Sept. 2013

  1. 1. Alexandre Gramfort http://alexandre.gramfort.net http://scikit-learn.org “Lire dans les pensées avec Scikit-Learn” “Mind Reading with Scikit-Learn” Paris Machine Learning Meetup - Sept. 2013
  2. 2. Alexandre Gramfort Mind Reading with the Scikit-Learn Basics of Functional MRI (fMRI) 2 Oxy. Hb Deoxy. Hb Neurons 3D volumes (1 every 1 or 2s) High spatial resolution (vox ⋍ 2mm) Scanner Nuclear Magnetic Resonance
  3. 3. courtesy of GaelVaroquauxhttp://www.youtube.com/watch?v=uhCF-zlk0jY
  4. 4. Alexandre Gramfort Mind Reading with the Scikit-Learn Learning from fMRI 4 Image, sound, task fMRI volumes Challenge: Learn and Predict from the fMRI data scanning Machine Learningstim Any variable: healthy?
  5. 5. Alexandre Gramfort Mind Reading with the Scikit-Learn Result from Miyawaki et al. Neuron 2008 5 http://www.youtube.com/watch?v=h1Gu1YSoDaY
  6. 6. Alexandre Gramfort Mind Reading with the Scikit-Learn Result from Miyawaki et al. Neuron 2008 6 • Some details about the data: • 2h of scanning • 1 image for 12s then 12s of rest • 800MB of raw data (200MB compressed) • 5,000 good voxels
  7. 7. Alexandre Gramfort Mind Reading with the Scikit-Learn Result from Nishimoto et al. 2011 7 http://www.youtube.com/watch?v=nsjDnYxJ0bo
  8. 8. Alexandre Gramfort Mind Reading with the Scikit-Learn Result from Nishimoto et al. 2011 8 • Some details about the data: • 30GB of stimuli (15 frames/s in .png for 3h) • about 4,000 volumes • about 10GB of raw data • 30,000 “good” voxels • > 3h in the scanner
  9. 9. Alexandre Gramfort Mind Reading with the Scikit-Learn Classification example with f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he objective is to be able to predict given an fMRI volume !5678*###############################3(%45678*-#9:#;+*"#/:9:# !"#$$%&'()*'+)#,-. FG4(H8&?#%*)((*#B?()?E#8C+I(@######54 F<5C7+4(#74(H8&?(H#=+A(=#J8?'#?4%(#?+4I(? ?'(#>(+?%4(#)7+&(@ F.*#?'8)#&+)(#74(H8&?(H#M#?4%(# FN(7(+?#>54#+==#)+C7=() FOD(4+I( ie. objective: Predict giveny = { 1, 1} x 2 Rp y = { 1, 1} !+,-#./ 0123(%45678*###############################3(%45678*-#9:#;+*"#/:9:# !"#$$%&'()*'+)#,-. FG4(H8&?#%*)((*#B?()?E#8C+I(@######54 F<5C7+4(#74(H8&?(H#=+A(=#J8?'#?4%(#?+4I(? ?'(#>(+?%4(#)7+&(@ F.*#?'8)#&+)(#74(H8&?(H#M#?4%(# FN(7(+?#>54#+==#)+C7=() FOD(4+I( Patient Controlsvs. Faces Housesvs. ... ...vs. 1 -1vs.
  10. 10. Demo on Haxby et al. Science 2001 Challenge: Predict the object category viewed Sample stimuli: Face House Chair Shoe
  11. 11. Alexandre Gramfort Mind Reading with the Scikit-Learn Miyawaki et al. 2008 with Scikit-Learn 11 < 250 Lines of codes
  12. 12. Alexandre Gramfort alexandre.gramfort@telecom-paristech.fr http://alexandre.gramfort.net http://www.github.com/agramfort @agramfort Contact:

×