FlintSlutzkyAccurate2012#

class torch_brain.datasets.FlintSlutzkyAccurate2012(root=None, recording_ids=None, transform=None, split_type='hand_velocity', dirname='flint_slutzky_accurate_2012', **kwargs)[source]#

Bases: torch_brain.datasets.mixins.SpikingDatasetMixin, torch_brain.datasets.dataset.Dataset

Motor cortex (M1) spiking activity and reaching kinematics from 1 monkey performing center-out reaching tasks.

Preprocessing

To download and prepare this dataset, run

brainsets prepare flint_slutzky_accurate_2012

Tasks: Center-Out

Brain Regions: M1

Dataset Statistics

  • Subjects: 1

  • Total Sessions: 5

  • Total Units: 957

  • Events: ~7.9M spikes, ~319k behavioral timestamps

Links

Reference

Flint, R. D., Lindberg, E. W., Jordan, L. R., Miller, L. E., & Slutzky, M. W. (2012). Accurate decoding of reaching movements from field potentials in the absence of spikes. Journal of Neural Engineering, 9(4), 046006.

Parameters:

  • root (Optional[str]) – Root directory for the dataset. Defaults to processed_dir from brainsets config.

  • recording_ids (Optional[list[str]]) – List of recording IDs to load.

  • transform (Optional[Callable]) – Data transformation to apply.

  • split_type (Optional[Literal['hand_velocity']]) – Which split type to use. Defaults to “hand_velocity”.

  • dirname (str) – Subdirectory for the dataset. Defaults to “flint_slutzky_accurate_2012”.

get_sampling_intervals(split=None)[source]#

Returns a dictionary of sampling intervals for each recording. This represents the intervals that can be sampled from each session.

This dictionary will be used by torch_brain’s Samplers to know where to sample from.

The default method returns intervals containing the entire domain of each recording. This behavior can be overridden by subclasses to give out custom sampling intervals.

Returns:

Dictionary mapping recording IDs to their time domain intervals.