ScaledCumulativeTraceReducer

class ScaledCumulativeTraceReducer(step_time: float, time_constant: float, amplitude: int | float | complex, scale: int | float | complex, criterion: OneToOne[Tensor], *, duration: float = 0.0, inclusive: bool = False, inplace: bool = False)

Bases: FoldReducer

Stores the trace over time, scaled by the input, considering all prior matches.

\[x(t) = x(t - \Delta t) \exp \left(-\frac{\Delta t}{\tau_x}\right) + (sh + A) \left[\lvert J(h) \right]\]

For the trace (state) \(x\) and observation \(h\).

Parameters:

• step_time (float) – length of the discrete step time, \(\Delta t\).

• time_constant (float) – time constant of exponential decay, \(\tau_x\).

• amplitude (int | float | complex) – value to add to trace for matching elements, \(A\).

• scale (int | float | complex) – multiplicative scale for contributions to trace, \(s\).

• criterion (OneToOne[torch.Tensor]) – function to test if the input is considered a match for the purpose of tracing, \(J\).

• duration (float, optional) – length of time over which results should be stored, in the same units as \(\Delta t\). Defaults to 0.0.

• inclusive (bool, optional) – if the duration should be inclusive. Defaults to False.

• inplace (bool, optional) – if write operations should be performed in-place. Defaults to False.

Note

The output of criterion must have a datatype (torch.dtype) of torch.bool.

property dt: float

Length of the simulation time step, in milliseconds.

Parameters:

value (float) – new simulation time step length.

Returns:

length of the simulation time step.

Return type:

float

fold(obs: Tensor, state: Tensor | None) → Tensor

Application of scaled cumulative trace.

Parameters:

• obs (torch.Tensor) – observation to incorporate into state.

• state (torch.Tensor | None) – state from the prior time step, None if no prior observations.

Returns:

state for the current time step.

Return type:

torch.Tensor

interpolate(prev_data: Tensor, next_data: Tensor, sample_at: Tensor, step_time: float) → Tensor

Exponential decay interpolation between observations.

Parameters:

• prev_data (torch.Tensor) – most recent observation prior to sample time.

• next_data (torch.Tensor) – most recent observation subsequent to sample time.

• sample_at (torch.Tensor) – relative time at which to sample data.

• step_time (float) – length of time between the prior and subsequent observations.

Returns:

interpolated data at sample time.

Return type:

torch.Tensor