brainpy.dyn.layers.NVAR#

class brainpy.dyn.layers.NVAR(num_in, delay, order=None, stride=1, constant=False, mode=BatchingMode, name=None)[source]#

Nonlinear vector auto-regression (NVAR) node.

This class has the following features:

  • it supports batch size,

  • it supports multiple orders,

Parameters
  • delay (int) – The number of delay step.

  • order (int, sequence of int) – The nonlinear order.

  • stride (int) – The stride to sample linear part vector in the delays.

  • constant (optional, float) – The constant value.

References

1

Gauthier, D.J., Bollt, E., Griffith, A. et al. Next generation reservoir computing. Nat Commun 12, 5564 (2021). https://doi.org/10.1038/s41467-021-25801-2

__init__(num_in, delay, order=None, stride=1, constant=False, mode=BatchingMode, name=None)[source]#

Methods

__init__(num_in, delay[, order, stride, ...])

clear_input()

get_delay_data(identifier, delay_step, *indices)

Get delay data according to the provided delay steps.

get_feature_names([for_plot])

Get output feature names for transformation.

load_states(filename[, verbose])

Load the model states.

nodes([method, level, include_self])

Collect all children nodes.

offline_fit(target, fit_record)

offline_init()

online_fit(target, fit_record)

online_init()

register_delay(identifier, delay_step, ...)

Register delay variable.

register_implicit_nodes(*nodes, **named_nodes)

register_implicit_vars(*variables, ...)

reset([batch_size])

Reset function which reset the whole variables in the model.

reset_local_delays([nodes])

Reset local delay variables.

reset_state([batch_size])

Reset the node state which depends on batch size.

save_states(filename[, variables])

Save the model states.

train_vars([method, level, include_self])

The shortcut for retrieving all trainable variables.

unique_name([name, type_])

Get the unique name for this object.

update(sha, x)

The function to specify the updating rule.

update_local_delays([nodes])

Update local delay variables.

vars([method, level, include_self])

Collect all variables in this node and the children nodes.

Attributes

global_delay_data

mode

Mode of the model, which is useful to control the multiple behaviors of the model.

name

Name of the model.