spynnaker.pyNN.models.neural_projections package

Subpackages

• spynnaker.pyNN.models.neural_projections.connectors package
  • Submodules
  • spynnaker.pyNN.models.neural_projections.connectors.abstract_connector module
  • spynnaker.pyNN.models.neural_projections.connectors.abstract_generate_connector_on_machine module
  • spynnaker.pyNN.models.neural_projections.connectors.all_to_all_connector module
  • spynnaker.pyNN.models.neural_projections.connectors.array_connector module
  • spynnaker.pyNN.models.neural_projections.connectors.csa_connector module
  • spynnaker.pyNN.models.neural_projections.connectors.distance_dependent_probability_connector module
  • spynnaker.pyNN.models.neural_projections.connectors.fixed_number_post_connector module
  • spynnaker.pyNN.models.neural_projections.connectors.fixed_number_pre_connector module
  • spynnaker.pyNN.models.neural_projections.connectors.fixed_probability_connector module
  • spynnaker.pyNN.models.neural_projections.connectors.from_list_connector module
  • spynnaker.pyNN.models.neural_projections.connectors.index_based_probability_connector module
  • spynnaker.pyNN.models.neural_projections.connectors.kernel_connector module
  • spynnaker.pyNN.models.neural_projections.connectors.multapse_connector module
  • spynnaker.pyNN.models.neural_projections.connectors.one_to_one_connector module
  • spynnaker.pyNN.models.neural_projections.connectors.small_world_connector module
  • Module contents

Submodules

spynnaker.pyNN.models.neural_projections.delay_afferent_application_edge module

class spynnaker.pyNN.models.neural_projections.delay_afferent_application_edge.DelayAfferentApplicationEdge(prevertex, delayvertex, label=None)

Bases: pacman.model.graphs.application.application_edge.ApplicationEdge

create_machine_edge(pre_vertex, post_vertex, label)

Create a machine edge between two machine vertices

Parameters:

• pre_vertex (pacman.model.graphs.machine.MachineVertex) – The machine vertex at the start of the edge
• post_vertex (pacman.model.graphs.machine.MachineVertex) – The machine vertex at the end of the edge
• label (str) – label of the edge

Returns:

The created machine edge

Return type:

pacman.model.graphs.machine.MachineEdge

spynnaker.pyNN.models.neural_projections.delay_afferent_machine_edge module

class spynnaker.pyNN.models.neural_projections.delay_afferent_machine_edge.DelayAfferentMachineEdge(pre_vertex, post_vertex, label, weight=1)

Bases: pacman.model.graphs.machine.machine_edge.MachineEdge, spynnaker.pyNN.models.abstract_models.abstract_filterable_edge.AbstractFilterableEdge, spynnaker.pyNN.models.abstract_models.abstract_weight_updatable.AbstractWeightUpdatable

filter_edge(graph_mapper)

Determine if this edge should be filtered out

Parameters:graph_mapper – the mapper between graphs Returns:True if the edge should be filtered Return type:bool

update_weight(graph_mapper)

Update the weight

spynnaker.pyNN.models.neural_projections.delayed_application_edge module

class spynnaker.pyNN.models.neural_projections.delayed_application_edge.DelayedApplicationEdge(pre_vertex, post_vertex, synapse_information, label=None)

Bases: pacman.model.graphs.application.application_edge.ApplicationEdge

add_synapse_information(synapse_information)

create_machine_edge(pre_vertex, post_vertex, label)

Create a machine edge between two machine vertices

Parameters:

• pre_vertex (pacman.model.graphs.machine.MachineVertex) – The machine vertex at the start of the edge
• post_vertex (pacman.model.graphs.machine.MachineVertex) – The machine vertex at the end of the edge
• label (str) – label of the edge

Returns:

The created machine edge

Return type:

pacman.model.graphs.machine.MachineEdge

synapse_information

spynnaker.pyNN.models.neural_projections.delayed_machine_edge module

class spynnaker.pyNN.models.neural_projections.delayed_machine_edge.DelayedMachineEdge(synapse_information, pre_vertex, post_vertex, label=None, weight=1)

Bases: pacman.model.graphs.machine.machine_edge.MachineEdge, spynnaker.pyNN.models.abstract_models.abstract_filterable_edge.AbstractFilterableEdge

filter_edge(graph_mapper)

Determine if this edge should be filtered out

Parameters:graph_mapper – the mapper between graphs Returns:True if the edge should be filtered Return type:bool

spynnaker.pyNN.models.neural_projections.projection_application_edge module

class spynnaker.pyNN.models.neural_projections.projection_application_edge.ProjectionApplicationEdge(pre_vertex, post_vertex, synapse_information, label=None)

Bases: pacman.model.graphs.application.application_edge.ApplicationEdge

An edge which terminates on an AbstractPopulationVertex.

add_synapse_information(synapse_information)

create_machine_edge(pre_vertex, post_vertex, label)

Create a machine edge between two machine vertices

Parameters:

• pre_vertex (pacman.model.graphs.machine.MachineVertex) – The machine vertex at the start of the edge
• post_vertex (pacman.model.graphs.machine.MachineVertex) – The machine vertex at the end of the edge
• label (str) – label of the edge

Returns:

The created machine edge

Return type:

pacman.model.graphs.machine.MachineEdge

delay_edge

n_delay_stages

synapse_information

spynnaker.pyNN.models.neural_projections.projection_machine_edge module

class spynnaker.pyNN.models.neural_projections.projection_machine_edge.ProjectionMachineEdge(synapse_information, pre_vertex, post_vertex, label=None, traffic_weight=1)

Bases: pacman.model.graphs.machine.machine_edge.MachineEdge, spynnaker.pyNN.models.abstract_models.abstract_filterable_edge.AbstractFilterableEdge, spynnaker.pyNN.models.abstract_models.abstract_weight_updatable.AbstractWeightUpdatable, spinn_front_end_common.interface.provenance.abstract_provides_local_provenance_data.AbstractProvidesLocalProvenanceData

filter_edge(graph_mapper)

Determine if this edge should be filtered out

Parameters:graph_mapper – the mapper between graphs Returns:True if the edge should be filtered Return type:bool

get_local_provenance_data()

Get an iterable of provenance data items

Returns:iterable of ProvenanceDataItem

synapse_information

update_weight(graph_mapper)

Update the weight

spynnaker.pyNN.models.neural_projections.synapse_information module

class spynnaker.pyNN.models.neural_projections.synapse_information.SynapseInformation(connector, synapse_dynamics, synapse_type, weight=None, delay=None)

Bases: object

Contains the synapse information including the connector, synapse type and synapse dynamics

connector

delay

synapse_dynamics

synapse_type

weight

Module contents

class spynnaker.pyNN.models.neural_projections.DelayAfferentApplicationEdge(prevertex, delayvertex, label=None)

Bases: pacman.model.graphs.application.application_edge.ApplicationEdge

create_machine_edge(pre_vertex, post_vertex, label)

Create a machine edge between two machine vertices

Parameters:

• pre_vertex (pacman.model.graphs.machine.MachineVertex) – The machine vertex at the start of the edge
• post_vertex (pacman.model.graphs.machine.MachineVertex) – The machine vertex at the end of the edge
• label (str) – label of the edge

Returns:

The created machine edge

Return type:

pacman.model.graphs.machine.MachineEdge

class spynnaker.pyNN.models.neural_projections.DelayAfferentMachineEdge(pre_vertex, post_vertex, label, weight=1)

Bases: pacman.model.graphs.machine.machine_edge.MachineEdge, spynnaker.pyNN.models.abstract_models.abstract_filterable_edge.AbstractFilterableEdge, spynnaker.pyNN.models.abstract_models.abstract_weight_updatable.AbstractWeightUpdatable

filter_edge(graph_mapper)

Determine if this edge should be filtered out

Parameters:graph_mapper – the mapper between graphs Returns:True if the edge should be filtered Return type:bool

update_weight(graph_mapper)

Update the weight

class spynnaker.pyNN.models.neural_projections.DelayedApplicationEdge(pre_vertex, post_vertex, synapse_information, label=None)

Bases: pacman.model.graphs.application.application_edge.ApplicationEdge

add_synapse_information(synapse_information)

create_machine_edge(pre_vertex, post_vertex, label)

Create a machine edge between two machine vertices

Parameters:

• pre_vertex (pacman.model.graphs.machine.MachineVertex) – The machine vertex at the start of the edge
• post_vertex (pacman.model.graphs.machine.MachineVertex) – The machine vertex at the end of the edge
• label (str) – label of the edge

Returns:

The created machine edge

Return type:

pacman.model.graphs.machine.MachineEdge

synapse_information

class spynnaker.pyNN.models.neural_projections.DelayedMachineEdge(synapse_information, pre_vertex, post_vertex, label=None, weight=1)

Bases: pacman.model.graphs.machine.machine_edge.MachineEdge, spynnaker.pyNN.models.abstract_models.abstract_filterable_edge.AbstractFilterableEdge

filter_edge(graph_mapper)

Determine if this edge should be filtered out

Parameters:graph_mapper – the mapper between graphs Returns:True if the edge should be filtered Return type:bool

class spynnaker.pyNN.models.neural_projections.ProjectionApplicationEdge(pre_vertex, post_vertex, synapse_information, label=None)

Bases: pacman.model.graphs.application.application_edge.ApplicationEdge

An edge which terminates on an AbstractPopulationVertex.

add_synapse_information(synapse_information)

create_machine_edge(pre_vertex, post_vertex, label)

Create a machine edge between two machine vertices

Parameters:

• pre_vertex (pacman.model.graphs.machine.MachineVertex) – The machine vertex at the start of the edge
• post_vertex (pacman.model.graphs.machine.MachineVertex) – The machine vertex at the end of the edge
• label (str) – label of the edge

Returns:

The created machine edge

Return type:

pacman.model.graphs.machine.MachineEdge

delay_edge

n_delay_stages

synapse_information

class spynnaker.pyNN.models.neural_projections.ProjectionMachineEdge(synapse_information, pre_vertex, post_vertex, label=None, traffic_weight=1)

Bases: pacman.model.graphs.machine.machine_edge.MachineEdge, spynnaker.pyNN.models.abstract_models.abstract_filterable_edge.AbstractFilterableEdge, spynnaker.pyNN.models.abstract_models.abstract_weight_updatable.AbstractWeightUpdatable, spinn_front_end_common.interface.provenance.abstract_provides_local_provenance_data.AbstractProvidesLocalProvenanceData

filter_edge(graph_mapper)

Determine if this edge should be filtered out

Parameters:graph_mapper – the mapper between graphs Returns:True if the edge should be filtered Return type:bool

get_local_provenance_data()

Get an iterable of provenance data items

Returns:iterable of ProvenanceDataItem

synapse_information

update_weight(graph_mapper)

Update the weight

class spynnaker.pyNN.models.neural_projections.SynapseInformation(connector, synapse_dynamics, synapse_type, weight=None, delay=None)

Bases: object

Contains the synapse information including the connector, synapse type and synapse dynamics

connector

delay

synapse_dynamics

synapse_type

weight