This page is a reference documentation. It only explains the class signature, and not how to use it. Please refer to the user guide for the big picture.
Implement search_light analysis using an arbitrary type of classifier.
mask_img : Niimg-like object
process_mask_img : Niimg-like object, optional
radius : float, optional
estimator : ‘svr’, ‘svc’, or an estimator object implementing ‘fit’
n_jobs : int, optional. Default is -1.
scoring : string or callable, optional
cv : cross-validation generator, optional
verbose : int, optional
The searchlight [Kriegeskorte 06] is a widely used approach for the study of the fine-grained patterns of information in fMRI analysis. Its principle is relatively simple: a small group of neighboring features is extracted from the data, and the prediction function is instantiated on these features only. The resulting prediction accuracy is thus associated with all the features within the group, or only with the feature on the center. This yields a map of local fine-grained information, that can be used for assessing hypothesis on the local spatial layout of the neural code under investigation.
Nikolaus Kriegeskorte, Rainer Goebel & Peter Bandettini. Information-based functional brain mapping. Proceedings of the National Academy of Sciences of the United States of America, vol. 103, no. 10, pages 3863-3868, March 2006
Fit the searchlight
imgs : Niimg-like object
y : 1D array-like
Get parameters for this estimator.
deep: boolean, optional
params : mapping of string to any
Set the parameters of this estimator.
The method works on simple estimators as well as on nested objects (such as pipelines). The former have parameters of the form <component>__<parameter> so that it’s possible to update each component of a nested object.