WeightBiasDelayMixin¶

class WeightBiasDelayMixin(weight: Tensor, bias: Tensor | None, delay: Tensor | None, requires_grad=False)[source]¶

Mixin for connections with weights, biases, and delays.

Parameters:

weight (torch.Tensor) – initial connection weights.
bias (torch.Tensor) – initial connection biases, if any.
delay (torch.Tensor) – initial connection delays, if any.
requires_grad (bool, optional) – if the parameters created require gradients. Defaults to False.

Caution

This must be added to a class which inherits from Module, and the constructor for this mixin must be called after the module constructor.

Note

This registers a parameter weight_. If either bias or delay is not None, parameters bias_ and delay_ are created respectively.

property delay: Parameter | None¶

Learnable connection delays.