aihwkit.inference.noise.base module

Base class for the phenomenological noise models for inference.

class aihwkit.inference.noise.base.BaseNoiseModel(g_converter=None)

Bases: object

Base class for phenomenological noise models for inference.

Parameters

g_converter (aihwkit.inference.converter.base.BaseConductanceConverter) –

apply_drift_noise(weights, nu_drift_list, t_inference)

Apply the expected drift noise to weights.

Uses the apply_drift_noise_to_conductances() on each of the conductance slices.

Parameters

• weights (torch.Tensor) – weights tensor (usually with programming noise already applied)

• nu_drift_list (List[torch.Tensor]) – list of drift nu for each conductance slice

• t_inference (float) – assumed time of inference (in sec)

Returns

weight tensor with drift noise applied

Return type

torch.Tensor

apply_drift_noise_to_conductance(g_prog, nu_drift, t_inference)

Apply the noise and drift up to the assumed inference time point.

Parameters

• g_prog (torch.Tensor) – Tensor of conductance values after programming (in \(\muS\))

• nu_drift (torch.Tensor) – drift nu

• t_inference (float) – assumed time of inference (in sec)

Returns

conductance Tensor with applied noise and drift

Return type

torch.Tensor

apply_noise(weights, t_inference)

Apply the expected noise.

Applies the noise to a non-perturbed conductance matrix weights at time of inference t_inference (in seconds) where 0 sec refers to the time when weight programming has finished.

Note

The drift coefficients and intermediate noises etc. are sampled for each application of this function anew from the distributions, thus it samples the expected noise and drift behavior at time t_inference but not a continual trajectory of a given device instance over time (having e.g. constant drift coefficients).

Parameters

• weights (torch.Tensor) –

• t_inference (float) –

Return type

torch.Tensor

apply_programming_noise(weights)

Apply the expected programming noise to weights.

Uses the apply_programming_noise_to_conductances() on each of the conductance slices.

Parameters

weights (torch.Tensor) – weights tensor

Returns

weight tensor with programming noise applied, and tuple of all drift coefficients (per conductances slice) that are determined during programming.

Return type

Tuple[torch.Tensor, List[torch.Tensor]]

apply_programming_noise_to_conductance(g_target)

Apply programming noise to a target conductance Tensor.

Parameters

g_target (torch.Tensor) – Target conductances

Returns

Tensor of sampled drift coefficients \(\nu\), one for each target conductance value.

Return type

torch.Tensor

generate_drift_coefficients(g_target)

Generate drift coefficients nu based on the target conductances.

Parameters

g_target (torch.Tensor) –

Return type

torch.Tensor