Echo State Network reservoirpy.ESN

class reservoirpy.ESN(

reservoir: Reservoir | None = None,

readout: Ridge | None = None,

feedback=False,

input_to_readout=False,

**kwargs,

)

Simple Echo State Network.

This class is provided as a wrapper for a simple reservoir connected to a readout.

Parameters:

• units (int, optional) – Number of reservoir units. If None, the number of units will be inferred from the W matrix shape.

• reservoir (Node, optional) – A Node instance to use as a reservoir, such as a Reservoir node.

• readout (Node, optional) – A Node instance to use as a readout, such as a Ridge node (only this one is supported).

• feedback (bool, defaults to False) – If True, the readout is connected to the reservoir through a feedback connection.

• input_to_readout (bool, defaults to False) – If True, the input is directly fed to the readout. See Input-to-readout connections.

• **kwargs – Arguments passed to the reservoir and readout.

See also

Reservoir, Ridge

Example

>>> from reservoirpy import ESN
>>>
>>> model = ESN(units=100, sr=0.9, ridge=1e-6)
>>>

Methods

initialize(x[, y])	Initializes a Model instance at runtime, using samples of data to infer all Node dimensions.
step([x])
run([x, iters, workers])
predict([x, iters])
fit(x[, y, warmup, workers])
partial_fit(x[, y])

Attributes

reservoir	A Reservoir or a NVAR instance.
readout	A Ridge instance.
feedback	Is readout connected to reservoir through feedback (False by default).
input_to_readout	Does the readout directly receives the input (False by default).
input_node	Input node, if input_to_readout is set to True
nodes
edges
inputs
outputs
named_nodes
trainable_nodes
execution_order
parents
children
is_trainable
is_multi_input
is_multi_output
is_parallel
initialized

feedback: bool

Is readout connected to reservoir through feedback (False by default).

initialize(

x: array(t, d) | array(s, t, d) | ~typing.Sequence[array(t, d)] | dict[str, array(t, d) | array(s, t, d) | ~typing.Sequence[array(t, d)]] | array(d) | dict[str, array(d)],

y: array(t, d) | array(s, t, d) | ~typing.Sequence[array(t, d)] | dict[str, array(t, d) | array(s, t, d) | ~typing.Sequence[array(t, d)]] | array(d) | dict[str, array(d)] | None = None,

)

Initializes a Model instance at runtime, using samples of data to infer all Node dimensions.

Parameters:

• x (numpy.ndarray or dict of numpy.ndarray) – A vector of shape (1, ndim) corresponding to a timestep of data, or a dictionary mapping node names to vector of shapes (1, ndim of corresponding node).

• y (numpy.ndarray or dict of numpy.ndarray, optional) – A vector of shape (1, ndim) corresponding to a timestep of target data, or a dictionary mapping node names to vector of shapes (1, ndim of corresponding node).

input_node: Input | None = None

Input node, if input_to_readout is set to True

input_to_readout: bool

Does the readout directly receives the input (False by default).

readout: TrainableNode

A Ridge instance.

reservoir: Node

A Reservoir or a NVAR instance.