DemixingPCA¶
In addition to systematically capturing the majority of the variance of the data, dPCA also exposes the dependence of the neural representation on task parameters such as stimuli, decisions, or rewards.
The model is output through the built-in model port.
More Info...
Version 1.1.0
Ports/Properties¶
data¶
Data to process.
grouping¶
Values in (segmented-)markers stream to keep. Trials for each value will be grouped together as though they come from the same trial condition. The grouping variable can be a list of lists to reshape the groups into multiple dimensions (e.g., stimulus x decision). Grouping is only used when training the model.
labels¶
Labels of feature axes; one character per axis.
join¶
Parameter combinations to join. If a data set has parametrized by time t and stimulus s, then dPCA will split the data into marginalizations corresponding to 't', 's' and 'ts'. At times, we want to join different marginalizations (like 's' and 'ts'), e.g. if we are only interested in the time-modulated stimulus components. In this case, we would pass {'ts' : ['s','ts']}.
regularizer¶
Regularization parameter. If None or 0, then no regularization is applied. For any float > 0, the regularization weight is regularizer*var(data). For any float < 0, the optimal regularization parameter is found during fitting (might take some time).
n_components¶
Number of components to keep. If n_components is {'all': int}, then the same number of components are kept in every marginalization. Otherwise, the dict allows to set the number of components in each marginalization (e.g. {'t' : 10, 'ts' : 5}).
component_sort¶
Override the default sorting of maginalization-types in the output. Each element in the list is a string from the set of keys provided to join + 'time'. The first len() dimensions of the output will contain the marginalization specified in this list, and the remaining dimensions will keep their original order. Items can be repeated (e.g. ['stimulus', 'stimulus', 'decision']). Follow this node with a SelectRange node to restrict the output to these components.
n_iter¶
Number of iterations for randomized SVD solver (sklearn)
initialize_once¶
Calibrate the model only once. If set to False, then this node will recalibrate itself whenever a non-streaming data chunk is received that has both training labels and associated training instances.
dont_reset_model¶
Do not reset the model when the preceding graph is changed. Normally, when certain parameters of preceding nodes are being changed, the model will be reset. If this is enabled, the model will persist, but there is a chance that the model is incompatible when input data format to this node has changed.
cond_field¶
The name of the instance data field that contains the conditions to be discriminated. This parameter will be ignored if the packet has previously been processed by a BakeDesignMatrix node.
set_breakpoint¶
Set a breakpoint on this node. If this is enabled, your debugger (if one is attached) will trigger a breakpoint.
metadata¶
User-definable meta-data associated with the node. Usually reserved for technical purposes.