ExponentialStandardization¶
Standardize the given data using an exponentially decaying window.
This filter aims to produce standardized output signals (that is, each channel/feature has approximately mean zero and variance one). This is based on the statistics of the past data, where more recent data is weighted more strongly. The time constant of this exponential weighting is an adjustible parameter. This filter is meant to be run on continuous data. That is, it should not be preceded by a Segmentation node. Version 1.1.0
Ports/Properties¶
data¶
Data to process.
forget_halftime¶
Time constant of filter, in seconds. Data that lies this many seconds in the past will be weighted half as much as the most recent data when designing the filter, and data twice as old will be weighted by 1/4, etc. Can also be thought of as the half-time of an exponentially weighted filter.
ignore_nans¶
If activated the data slices containing nan values are ignored.
across_all_chs¶
If activated the standardization is performed across all entries in the non-time axes, ie., the mean and standard deviation is calculated over the entire tensor snapshot.
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.