1 / 22

MVPA / MVPD – Multivariate pattern decoding

MVPA / MVPD – Multivariate pattern decoding. Session 13, 3.7.2008 Christian Kaul. MATLAB for Cognitive Neuroscience. Outline. What is MVPD What types of classifiers are there? MVPD in fMRI How to design an experiment – 2 Examples The MVPD MatLab “toolbox”

miles
Download Presentation

MVPA / MVPD – Multivariate pattern decoding

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. MVPA / MVPD – Multivariate pattern decoding Session 13, 3.7.2008 Christian Kaul MATLAB for Cognitive Neuroscience

  2. Outline • What is MVPD • What types of classifiers are there? • MVPD in fMRI • How to design an experiment – 2 Examples • The MVPD MatLab “toolbox” • Common problems when thinking about MVPD of fMRI data

  3. MVPD – Multivariate pattern decoding • Also known as MVPA with A for Analysis – however if you enter MVPA into Google you end up here:

  4. MVPD – Multivariate pattern decoding • What is MVPD? • Methodology in which an algorithm is trained to tell two or more conditions from each other. • The algorithm is then presented with a new set of data and categorises/classifies it into the conditions previously learned. • MVPD is a relatively new tool in fMRI, however note that Pattern Classification as such has long been developed and used in Artificial Intelligence and Neuronal Networks.

  5. What types of classifiers are there? • The most common classifiers used for fMRI data are • LDA (Linear Discriminant Analysis) and • SVM (Support Vector Machines). algorithm: maximize margin! • Both are generally doing a good job. • LDA finds a solution based on linear combinations of features only. • However SVMs also take non-linear effects into account. This is largely done by mapping the information into a higher dimensional space (feature space).

  6. Non-linear SVMs - Feature space 2 examples: Downside of non-linear SVMs: There are more and more parameters to be optimized during learning.

  7. MVPD in fMRI • In situations we do find a univariate effect, a multivariate effect is unlikely to reveal anything new! • But when conventional analysis is not feasible, multivariate analysis might be an option. • What are we actually measuring? • What does a “pattern of brain activity mean? • Assumption: • Feature sensitive information is present in BOLD signal

  8. From fMRI data to a brain pattern. Pattern Multivoxel fMRI data Distribution of selective cells might be uneven (biased sampling)

  9. From fMRI data to a brain pattern. Result: Accuracy of decoding Raw fMRI data Classification Multivoxel fMRI data Classifier N-fold cross-validation Pattern %-accuracy result

  10. What questions can (& cannot) be answered with multivariate pattern analysis? • Feature sensitive information is present in BOLD signal (biased sampling) • Multivariate decodingextracts this info • Examples: • “What have I seen?” Decoding of visual input make the majority of publications (basic features, categories, entire natural pictures). • “What have I heard/ felt/ …?” Decoding of other features specific sensitive input should be possible. • “What am I going to do next?” Decisions seem to be coded in distinctive patterns of brain activity. Haynes & Rees (2005) Mean signal LDA

  11. Multivariate pattern analysis – how to design an experiment • Other then with conventional analysis we are asking a different question: Does the pattern of activity contain meaningful information we can extract?  Not the level of brain activity is addressed, but the pattern of information within the activity.

  12. Example 1 – visual features Question: • Does feature selective information (left vs. right tilted orientation as measured by decoding from BOLD signal) for the irrelevant annulus change between the two central load conditions? • Decoding objective: • Is feature selective information reduced in high load condition?

  13. Multivariate Decodingexample Result: actual expected Low Accuracy High 1 50 100 % correct decoded N voxels Result: Feature selective info present and decoded (…but slightly confusing) Number of voxels

  14. Question: Example 2 - intentions • At the beginning of each trial, the word “select” was presented that instructed the subjects to freely and covertly choose one of two possible tasks, addition or subtraction. From the button press, it was possible to determine the covert intention of the subject during the previous delay period. • Decoding objective : • Can subjects decision be decoded? Haynes et al, 2007

  15. Example 2, Result • In the anterior medial prefrontal cortex decoding during the delay (green bars) was highest but was at chance level during the task execution (red bars) after onset of the task-relevant stimuli. In contrast posterior & superior medial prefrontal cortex (MPFCp) encoded the chosen task only once it had entered the stage of execution, but not during the delay period. • Results presented with “searchlight” approach: A spherical searchlight centered on one voxel is used to define a local neighborhood.

  16. The MVPD MatLab “toolbox” • During the last few months I have written a set of MatLab- functions to perform multivariate data analysis with “any” suitable data (work in progress). • As the packet is quite complex and lengthy I’m only introducing the basic control-script. It is quite easy to follow the workflow in this control-script as a demonstration of how MVPD can look like. •  If anyone is interested in working with the code, please refer to course webpage, or, • as the “toolbox” is not complete yet: for the newest version contact me directly: c.kaul@ucl.ac.uk

  17. The common problems when thinking about MVPD of fMRI data • Decoding of what? TR, block average, betas. • Overfitting - too many features at too few data samples. • Voxel selection.

  18. The common problems when thinking about MVPD of fMRI data: TR, BLOCK or BETA? • In principle there are 3 different strategies how to get your brain pattern: single TRs (raw data), averaged blocks of TRs, betas (spm-estimates). single TRs avg. BLOCKs BETAs Noise Number of observations

  19. The common problems when thinking about MVPD of fMRI data - OVERFITTING • (1) an SVM classifier is unstable on a small-sized training set; • (2) SVM’s optimal hyper-plane may be biased when the positive feedback samples are much less than the negative samples • (3) overfitting happens because the number of feature dimensions is much higher than the size of the training set.

  20. Over-fitting and Under-fitting • To avoid overfitting, cross-validation is used to evaluate the fitting provided by each parameter value set tried during the grid or pattern search process.

  21. The common problems when thinking about MVPD of fMRI data: VOXEL SELECTION • To reduce feature input dimensionality it is common to preselect voxels: • ROI based selection on voxels • ROI must be defined independent from classification • Threshold based selection of voxels • threshold must be independent from classification • Searchlight approach: A fixed sphere is moved over the brain, voxel-by-voxel • Data has to be corrected for multiple comparisons as each data point is used multiple times.

  22. Thanks – enjoy this sunny afternoon!

More Related