We need your help! 🔥
Please consider disabling your ad-blocker to support this website! 🔑
We are a free, community-supported website! 🥰
We only display small unobtrusive ads which help us stay online! 💯
Thank you in advance! ❤️
Evolutionary Learning
Explicit Components
Loop
Octopus
Supervised Learning
Utilities
View

Breeder Settings - All (oEL)

Settings for the NEAT Algorithm to evolve an ANN

Inputs

NameIDDescriptionType
connectionWeightRangeconnectionWeightRangeconnectionWeightRangeNumber
pOffspringAsexualpOffspringAsexualpOffspringAsexualNumber
pOffspringSexualpOffspringSexualpOffspringSexualNumber
pInterspeciesMatingpInterspeciesMatingpInterspeciesMatingNumber
PopInterConPopInterConpInitialPopulationInterconnectionsNumber
pMutateConnectionWeightspMutateConnectionWeightspMutateConnectionWeightsNumber
pMutateAddNodepMutateAddNodepMutateAddNodeNumber
pMutateAddModulepMutateAddModulepMutateAddModuleNumber
pMutateAddConnectionpMutateAddConnectionpMutateAddConnectionNumber
pMutateDeleteConnectionpMutateDeleteConnectionpMutateDeleteConnectionNumber
pMutateDeleteSimpleNeuronpMutateDeleteSimpleNeuronpMutateDeleteSimpleNeuronNumber
connectionMutationParamsconnectionMutationParamsEach branch holds parameters for a type of mutation; See the template file for a ready-made. 0: activation proportion [probability of group, 0-1, fraction per total sum approach], 1: perturbation type [0-JiggleEven, 1-JiggleNormalDistribution, 2-Reset], 2: selection type [0-Proportional, 1-Fixed Quantity], 3: proportion [% of connections to be mutated], 4: quantity [how many connections should be mutated], 5: perturbation amount [how much will be added/subtracted to/from the connection weight], 6: sigma [Standard deviation to randomly sample, sample being added/subtracted to connection weight]Number
compatibilityThresholdcompatibilityThresholdcompatibilityThresholdNumber
compatibilityDisjointCoeffcompatibilityDisjointCoeffcompatibilityDisjointCoeffNumber
compatibilityExcessCoeffcompatibilityExcessCoeffcompatibilityExcessCoeffNumber
compatibilityWeightDeltaCoeffcompatibilityWeightDeltaCoeffcompatibilityWeightDeltaCoeffNumber
elitismProportionelitismProportionelitismProportionNumber
selectionProportionselectionProportionselectionProportionNumber
targetSpeciesCountMinPercenttargetSpeciesCountMinPercenttargetSpeciesCountMin in Percent of population sizeNumber
pruningPhaseBeginComplexityThresholdpruningPhaseBeginComplexityThresholdpruningPhaseBeginComplexityThresholdNumber
pruningPhaseBeginFitnessStagnationThresholdpruningPhaseBeginFitnessStagnationThresholdpruningPhaseBeginFitnessStagnationThresholdInteger
pruningPhaseEndComplexityStagnationThresholdpruningPhaseEndComplexityStagnationThresholdpruningPhaseEndComplexityStagnationThresholdInteger
speciesExtinctionAgespeciesExtinctionAgespeciesExtinctionAgeInteger
enablePruningenablePruningenablePruningBoolean
Eval MutatedReTriesEval MutatedReTriesDuring Breeding, if an evaluation is invalid, how often should evaluation be retried with a mutated version of the initial failed NeatGenome?Integer

Outputs

NameIDDescriptionType
SettingsSSettings for the evolution of NetworksCPPN evolution parameters

Site design © Robin Rodricks.   Octopus and associated data © 2024 Robert Vierlinger.  
Rhinoceros and Grasshopper are registered trademarks of Robert McNeel & Associates.  Hosted by GitHub

Report an Issue  |  Terms of Service