RandomInput

Description

Randomly inject input to the network. Neurons’ dynamic receiving input will be heavily driven by the inputting signal. Injecting signal to only part of the neuron will result in more versatile and hierarchical dynamics. See A Versatile Hub Model For Efficient Information Propagation And Feature Selection

Parameters

Inherited Parameters

This class inherits all parameters from BaseStruct. See BaseStruct for more details.

Other Parameters

Parameter Default Type Description
input_spar 1 float Input sparsity. Percentage of neurons that receive input.
readout_spar 1 float Readout sparsity. Percentage of neurons that readout from.
hidden_spar 1 float Hidden sparsity. Percentage of edges that are non-zero.
overlap True boolean Whether a neuron can receive input and readout from.

results matching ""

    No results matching ""