bound_power¶
- bound_power(param: Tensor, pos: Tensor, neg: Tensor, max: float | None, min: float | None, *, upper_power: float, lower_power: float, **kwargs) Tensor[source]¶
Computes the scaled update of power parameter dependence.
This is sometimes also referred to as “soft parameter dependence”.
\[U = (P_\text{max} - P)^{\mu_+} U_+ - (P - P_\text{min})^{\mu_-} U_-\]- Parameters:
param (torch.Tensor) – parameter with update bounding, \(P\).
pos (torch.Tensor) – potentiative update being applied, \(U_+\).
neg (torch.Tensor) – depressive update being applied, \(U_-\).
max (float | None) – value of the upper bound, \(P_\text{max}\).
min (float | None) – value of the lower bound, \(P_\text{min}\).
upper_power (float) – exponent of upper-bound parameter dependence, \(\mu_+\).
lower_power (float) – exponent of lower-bound parameter dependence, \(\mu_-\).
- Returns:
bounded update.
- Return type: