createNode: Function to create some node

In reservoirnet: Reservoir Computing and Echo State Networks

Function to create some node

Description

Function to create some node

Usage

createNode(
  nodeType = c("Ridge"),
  units = NULL,
  lr = 1,
  sr = NULL,
  otputDim = NULL,
  inputDim = NULL,
  name = NULL,
  ridge = 0,
  inputBias = TRUE,
  input_scaling = TRUE,
  input_connectivity = 0.1,
  rc_connectivity = 0.1,
  activation = "tanh",
  dtype = "float64",
  seed = NULL,
  ...
)

Arguments

nodeType	Type of node. Default is "Ridge".
units	(int) optional Number of reservoir units. If None, the number of units will be infered from the W matrix shape.
lr	(float) default to 1.0 Neurons leak rate. Must be in :math:[0, 1].
sr	(float) optional Spectral radius of recurrent weight matrix.
otputDim	Output dimension of the Node. Dimension of its state.
inputDim	Input dimension of the Node.
name	Name of the Node. It must be a unique identifier.
ridge	float, default to 0.0. L2 regularization parameter.
inputBias	bool, default to TRUE. If TRUE, then a bias parameter will be learned along with output weights.
input_scaling	float or array-like of shapes (features), default to 1.0. Input gain. An array of the same dimension as the inputs can be used to set up different input scaling for each feature.
input_connectivity	float, default to 0.1. Connectivity of input neurons, i.e. ratio of input neurons connected to reservoir neurons. Must be between 0 and 1.
rc_connectivity	float, default to 0.1. Connectivity of recurrent weight matrix, i.e. ratio of reservoir neurons connected to other reservoir neurons, including themselves. Must be between 0 and 1.
activation	str 'tanh'. Reservoir units activation function. Should be a activationsfunc function name ('tanh', 'identity', 'sigmoid', 'relu', 'softmax', 'softplus').
dtype	Numerical type for node parameters
seed	set random seed
...	Others params

Value

A node generated by reservoirpy python module.

Examples

if(interactive()){
readout <- reservoirnet::createNode("Ridge")
}

reservoirnet documentation built on April 4, 2023, 5:12 p.m.