NeighbourhoodManager

Full Name

neuroptimiser.core.processes.NeighbourhoodManager

Description

class NeighbourhoodManager

Bases: AbstractProcess

Neighbourhood Manager Process

This process manages the neighbourhood of units based on a weight matrix. It computes the number of neighbours for each unit and stores the indices of the neighbours.

Inports

p_inInPort

Input port for the position tensor.

fp_inInPort

Input port for the fitness tensor.

Variables

weight_matrixVar

Variable for the weight matrix used to determine neighbourhoods.

neighbour_indicesVar

Variable for storing the indices of neighbours for each unit.

Outports

p_outOutPort

Output port for the position tensor of neighbours.

fp_outOutPort

Output port for the fitness tensor of neighbours.

See also

neuroptimiser.core.models.PyNeighbourhoodManagerModel

Model implementation of the NeighbourhoodManager process.

__init__(weights, **kwargs)

Initialise the NeighbourhoodManager with the given parameters.

Parameters:

weights (np.ndarray) – Weight matrix for the neighbourhoods. It should be a 2D numpy array where each row represents the weights of a unit to its neighbours.

Keyword Arguments:

**kwargs (dict, optional) – Additional keyword arguments to be passed to the parent class AbstractProcess.

reset() → None

Reset the NeighbourhoodManager to its initial state.

This method is currently a placeholder and does not perform any operations for compatibility purposes.