Decoding#

Decoding and encoding, including machine learning and receptive fields.

CSP([n_components, reg, log, cov_est, ...])

M/EEG signal decomposition using the Common Spatial Patterns (CSP).

Transformer to compute event-matched spatial filters.

FilterEstimator(info, l_freq, h_freq[, ...])

Estimator to filter RtEpochs.

Compute and store patterns from linear models.

PSDEstimator([sfreq, fmin, fmax, bandwidth, ...])

Compute power spectral density (PSD) using a multi-taper method.

Scaler([info, scalings, with_mean, with_std])

Standardize channel data.

TemporalFilter([l_freq, h_freq, sfreq, ...])

Estimator to filter data array along the last dimension.

TimeFrequency(freqs[, sfreq, method, ...])

Time frequency transformer.

Use unsupervised spatial filtering across time and samples.

Transform n-dimensional array into 2D array of n_samples by n_features.

ReceptiveField(tmin, tmax, sfreq[, ...])

Fit a receptive field model.

TimeDelayingRidge(tmin, tmax, sfreq[, ...])

Ridge regression of data with time delays.

SlidingEstimator(base_estimator[, scoring, ...])

Search Light.

Generalization Light.

SPoC([n_components, reg, log, ...])

Implementation of the SPoC spatial filtering.

SSD(info, filt_params_signal, filt_params_noise)

Signal decomposition using the Spatio-Spectral Decomposition (SSD).

XdawnTransformer([n_components, reg, ...])

Implementation of the Xdawn Algorithm compatible with scikit-learn.

SpatialFilter(info, filters, *[, evals, ...])

Container for spatial filter weights (evecs) and patterns.

Functions that assist with decoding and model fitting:

compute_ems(epochs[, conditions, picks, ...])

Compute event-matched spatial filter on epochs.

cross_val_multiscore(estimator, X[, y, ...])

Evaluate a score by cross-validation.

get_coef(estimator[, attr, ...])

Retrieve the coefficients of an estimator ending with a Linear Model.