ReservoirPy Nodes (reservoirpy.nodes)#

Reservoirs#

Reservoir(units, lr, sr, input_scaling, ...)

Pool of leaky-integrator neurons with random recurrent connexions.

NVAR(delay, order[, strides, input_dim, name])

Non-linear Vector AutoRegressive machine.

IPReservoir(units, sr, lr, mu, sigma, ...[, ...])

Pool of neurons with random recurrent connexions, tuned using Intrinsic Plasticity.

LocalPlasticityReservoir(units, local_rule, ...)

A reservoir that learns its recurrent weights W through a local learning rule selected by the learning_rule hyperparameter.

ES2N(units, proximity, sr, input_scaling, ...)

Edge of Stability Echo State Network.

Offline readouts#

Ridge([ridge, fit_bias, Wout, bias, ...])

A single layer of neurons learning with Tikhonov linear regression.

ScikitLearnNode(model[, output_dim, name])

A node interfacing a scikit-learn linear model that can be used as an offline readout node.

Online readouts#

LMS([learning_rate, Wout, bias, fit_bias, ...])

Single layer of neurons learning connections using Least Mean Squares algorithm.

RLS([alpha, Wout, bias, fit_bias, ...])

Single layer of neurons learning connections using Recursive Least Squares algorithm.

Activation functions#

Tanh([name])

Hyperbolic tangent activation function.

Sigmoid([name])

Sigmoid activation function.

Softmax([beta, name])

Softmax activation function.

Softplus([name])

Softplus activation function.

ReLU([name])

ReLU activation function.

Identity([name])

Identity function.

Input and Output#

Input([name])

Node feeding input data to other nodes in the models.

Output([name])

Convenience node which can be used to add an output to a model.