reservoirpy.nodes.Softmax

class reservoirpy.nodes.Softmax(beta=1.0, name: str | None = None)

Softmax activation function.

\[y_k = \frac{e^{\beta x_k}}{\sum_{i=1}^{n} e^{\beta x_i}}\]

Parameters:

• beta (float, default to 1.0) – Beta parameter of softmax.

• name (str, optional) – Node name.

Methods

__init__([beta, name])
initialize(x[, y])	Define input and output dimensions, and instantiate variables.
predict([x, iters, workers])	Alias for run()
reset()	Reset all Node state
run([x, iters, workers])	Run the Node on a sequence of data.
step([x])	Call the Node function on a single step of data and update the state of the Node.

Attributes

initialized	True if the Node has been initialized
input_dim	Expected dimension of the Node input.
name	Optional name of the Node.
output_dim	Expected dimension of the Node input.
state	Current state of the Node.

initialize(

x: Array2D | Array3D | Sequence[Timeseries] | Array1D,

y: None = None,

)

Define input and output dimensions, and instantiate variables.

Only called once, before fitting or running the node.

Parameters:

• x (array of shape (input_dim,) or (timestep, input_dim)) – Input data to the node.

• y (None) – Training data to the node. As it is not a trainable node, y is expected to be None.

initialized: bool = False

True if the Node has been initialized

input_dim: int = None

Expected dimension of the Node input. Can be None before initialization

name: str | None = None

Optional name of the Node.

output_dim: int = None

Expected dimension of the Node input. Can be None before initialization

predict(

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

iters: int | None = None,

workers=1,

) → array(t, d) | array(s, t, d) | ~typing.Sequence[array(t, d)]

Alias for run()

Run the Node on a sequence of data. Can update the state of the Node several times.

Parameters:

• x (array-like of shape ([n_inputs,] timesteps, input_dim) or list of) – arrays of shape (timesteps, input_dim), optional A sequence of data of shape (timesteps, features).

• iters (int, optional) – If x is None, a dimensionless timeseries of length iters is used instead.

• workers (int, default to 1) – Number of workers used for parallelization. If set to -1, all available workers (threads or processes) are used.

Returns:

A sequence of output vectors.

Return type:

array of shape ([n_inputs,] timesteps, output_dim) or list of arrays

reset() → dict[str, ndarray]

Reset all Node state

Returns:

dict[str, np.array]

Return type:

previous state of the Node.

run(

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

iters: int | None = None,

workers=1,

) → array(t, d) | array(s, t, d) | ~typing.Sequence[array(t, d)]

Run the Node on a sequence of data. Can update the state of the Node several times.

Parameters:

• x (array-like of shape ([n_inputs,] timesteps, input_dim) or list of arrays of shape (timesteps, input_dim), optional) – A timeseries, array of shape (timesteps, features), or a sequence of timeseries. Input of the Node.

• iters (int, optional) – If x is None, a dimensionless timeseries of length iters is used instead.

• workers (int, default to 1) – Number of workers used for parallelization. If set to -1, all available workers (threads or processes) are used.

Returns:

A sequence of output vectors.

Return type:

array of shape ([n_inputs,] timesteps, output_dim) or list of arrays

state: dict[str, ndarray]

Current state of the Node. Must have “out” as one of the keys.

step(x: array(d) | None = None)

Call the Node function on a single step of data and update the state of the Node.

Parameters:

x (array of shape (input_dim,), optional) – One single step of input data. If None, an empty array is used instead and the Node is assumed to have an input_dim of 0

Returns:

An output vector.

Return type:

array of shape (output_dim,)