LengthDelay

class brainpy.math.LengthDelay(delay_target, delay_len, initial_delay_data=None, name=None, batch_axis=None, update_method='rotation')

Delay variable which has a fixed delay length.

Parameters:

• delay_target (Union[Array, Array]) – The initial delay data.

• delay_len (int) – The maximum delay length.

• initial_delay_data (Union[float, int, bool, Array, Array, Callable]) –

  The delay data. It can be a Python number, like float, int, boolean values. It can also be arrays. Or a callable function or instance of Connector. A callable will be invoked as initial_delay_data(shape, dtype=...) when its signature accepts a dtype keyword (e.g. Initializer/Connector instances), and as initial_delay_data(shape) otherwise (e.g. a plain lambda shape: ...). Note that initial_delay_data should be arranged as the following way:

  delay = 1             [ data
  delay = 2               data
  ...                     ....
  ...                     ....
  delay = delay_len-1     data
  delay = delay_len       data ]
  

  Changed in version 2.2.3.2: The data in the previous version of LengthDelay is:

  delay = delay_len     [ data
  delay = delay_len-1     data
  ...                     ....
  ...                     ....
  delay = 2               data
  delay = 1               data ]
  

namestr

The delay object name.

batch_axisint

The batch axis. If not provided, it will be inferred from the delay_target.

update_methodstr

The method used for updating delay.

See also

TimeDelay

property delay_shape

The data shape of this delay variable.

property delay_target_shape

The data shape of the delay target.

retrieve(delay_len, *indices)

Retrieve the delay data acoording to the delay length.

Parameters:

delay_len (int, ArrayType) – The delay length used to retrieve the data.

update(value=None)

Update delay variable with the new data.

Parameters:

value (Union[Number, Array, Array]) – The value of the latest data, used to update this delay variable.