ReservoirPy Nodes (reservoirpy.nodes
)#
Reservoirs#
|
Pool of leaky-integrator neurons with random recurrent connexions. |
|
Non-linear Vector AutoRegressive machine. |
|
Pool of neurons with random recurrent connexions, tuned using Intrinsic Plasticity. |
Offline readouts#
|
A single layer of neurons learning with Tikhonov linear regression. |
|
A node interfacing a scikit-learn linear model that can be used as an offline readout node. |
Online readouts#
|
Single layer of neurons learning connections using Least Mean Squares algorithm. |
|
Single layer of neurons learning connections using Recursive Least Squares algorithm. |
|
Single layer of neurons learning connections through online learning rules. |
Optimized ESN#
|
Echo State Networks as a Node, with parallelization of state update. |
Activation functions#
|
Hyperbolic tangent activation function. |
|
Sigmoid activation function. |
|
Softmax activation function. |
|
Softplus activation function. |
|
ReLU activation function. |
|
Identity function. |
Input and Output#
|
Node feeding input data to other nodes in the models. |
|
Convenience node which can be used to add an output to a model. |
Operators#
|
Concatenate vector of data along feature axis. |
|
Delays the data transmitted through this node without transformation. |