spynnaker.pyNN.models.neuron.structural_plasticity.synaptogenesis.elimination package

Submodules

spynnaker.pyNN.models.neuron.structural_plasticity.synaptogenesis.elimination.abstract_elimination module

class spynnaker.pyNN.models.neuron.structural_plasticity.synaptogenesis.elimination.abstract_elimination.AbstractElimination[source]

Bases: object

An elimination rule

get_parameter_names()[source]

Return the names of the parameters supported by this rule

Return type:iterable(str)
get_parameters_sdram_usage_in_bytes()[source]

Get the amount of SDRAM used by the parameters of this rule

vertex_executable_suffix

The suffix to be appended to the vertex executable for this rule

write_parameters(spec, weight_scale)[source]

Write the parameters of the rule to the spec

spynnaker.pyNN.models.neuron.structural_plasticity.synaptogenesis.elimination.random_by_weight_elimination module

class spynnaker.pyNN.models.neuron.structural_plasticity.synaptogenesis.elimination.random_by_weight_elimination.RandomByWeightElimination(threshold, prob_elim_depressed=0.0245, prob_elim_potentiatiated=0.00013600000000000003)[source]

Bases: spynnaker.pyNN.models.neuron.structural_plasticity.synaptogenesis.elimination.abstract_elimination.AbstractElimination

Elimination Rule that depends on the weight of a synapse

Parameters:
  • threshold – Below this weight is considered depression, above or equal to this weight is considered potentiation (or the static weight of the connection on static weight connections)
  • prob_elim_depressed – The probability of elimination if the weight has been depressed (ignored on static weight connections)
  • prob_elim_potentiatiated – The probability of elimination of the weight has been potentiated or has not changed (and also used on static weight connections)
get_parameter_names()[source]

Return the names of the parameters supported by this rule

Return type:iterable(str)
get_parameters_sdram_usage_in_bytes()[source]

Get the amount of SDRAM used by the parameters of this rule

vertex_executable_suffix

The suffix to be appended to the vertex executable for this rule

write_parameters(spec, weight_scale)[source]

Write the parameters of the rule to the spec

Module contents

class spynnaker.pyNN.models.neuron.structural_plasticity.synaptogenesis.elimination.AbstractElimination[source]

Bases: object

An elimination rule

get_parameter_names()[source]

Return the names of the parameters supported by this rule

Return type:iterable(str)
get_parameters_sdram_usage_in_bytes()[source]

Get the amount of SDRAM used by the parameters of this rule

vertex_executable_suffix

The suffix to be appended to the vertex executable for this rule

write_parameters(spec, weight_scale)[source]

Write the parameters of the rule to the spec

class spynnaker.pyNN.models.neuron.structural_plasticity.synaptogenesis.elimination.RandomByWeightElimination(threshold, prob_elim_depressed=0.0245, prob_elim_potentiatiated=0.00013600000000000003)[source]

Bases: spynnaker.pyNN.models.neuron.structural_plasticity.synaptogenesis.elimination.abstract_elimination.AbstractElimination

Elimination Rule that depends on the weight of a synapse

Parameters:
  • threshold – Below this weight is considered depression, above or equal to this weight is considered potentiation (or the static weight of the connection on static weight connections)
  • prob_elim_depressed – The probability of elimination if the weight has been depressed (ignored on static weight connections)
  • prob_elim_potentiatiated – The probability of elimination of the weight has been potentiated or has not changed (and also used on static weight connections)
get_parameter_names()[source]

Return the names of the parameters supported by this rule

Return type:iterable(str)
get_parameters_sdram_usage_in_bytes()[source]

Get the amount of SDRAM used by the parameters of this rule

vertex_executable_suffix

The suffix to be appended to the vertex executable for this rule

write_parameters(spec, weight_scale)[source]

Write the parameters of the rule to the spec