Examples¶

Some introduction to the encoding/decoding framework.

Fit the residual covariance matrix

Stimulus decoding using stimulus mask

Linear encoding model

Create a simple Gaussian Prf encoding model

Invert encoding model

Decoding of stimuli from neural data

Recontruct a 2D visual stimulus from real fMRI data

Fit a 2D PRF model

Fisher information to estimate precision of encoding parameters across stimulus space

Different flavors of visual population receptive field models

Decoding 2D stimuli from neural data

End-to-end decoding pipeline on real data¶

Three connected examples that walk through a full encoding-model decoding pipeline on a small extract of single-trial fMRI data (numerosity task, right numerosity-tuned parietal cortex):

Select responsive voxels from whole-brain R² by fitting a 2-component mixture and picking a threshold (FDR or posterior).
Decode trial-wise stimulus posteriors using a noise model whose covariance is regularised by geodesic distance on the cortical surface.
Quantify expected decoding uncertainty by simulating from the fitted model and re-decoding.

Each example is self-contained but share the same demo dataset, which is downloaded on first run via braincoder.utils.data.load_dehollander2024_npc.

Voxel selection via a 2-component R² mixture model

Expected decoding uncertainty via simulate + decode

Geodesic-regularised noise model for trial-wise decoding

Gallery generated by Sphinx-Gallery