standardize

Contents

standardize#

class brainstate.nn.standardize(x, axis=-1, variance=None, epsilon=1e-05, where=None)[source]#

Standardize (normalize) an array.

Normalizes an array by subtracting the mean and dividing by the standard deviation \(\sqrt{\mathrm{variance}}\).

Parameters:

  • x (Array | ndarray | bool | number | bool | int | float | complex | Quantity) – Input array.

  • axis (int | tuple[int, ...] | None) – The axis or axes along which to compute the mean and variance. Default is -1.

  • variance (Array | ndarray | bool | number | bool | int | float | complex | Quantity | None) – Pre-computed variance. If None, variance is computed from x.

  • epsilon (Array | ndarray | bool | number | bool | int | float | complex | Quantity) – A small constant added to the variance to avoid division by zero. Default is 1e-5.

  • where (Array | ndarray | bool | number | bool | int | float | complex | Quantity | None) – Elements to include in the computation.

Returns:

Standardized array with the same shape as the input.

Return type:

Array | Quantity

Contents