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

Network Learning (oSL)

Supervised example training of a Network by multi-core resilient propagation algorithm, using the Encog library by Jeff Heaton

Inputs

NameIDDescriptionType
InputInputInput Values [x lists (x = number of training samples) of y numbers (y = dimensionality of sample input); Input and Output can be one or many dimensional, and the number of dimensions can be different]Number
OutputOutputOutput Values [x lists (x = number of training samples) of z numbers (z = dimensionality of sample output); Input and Output can be one or many dimensional, and the number of dimensions can be different]Number
LayersLayersHidden Layer CountInteger
NodesNodesNode Count per Hidden Layer, 0 = Maximum of Input and Output DimensionalityInteger
SeedSeedRandom SeedInteger
SeedNetSeedNetSeed Network to continue training on it; a seed model overrides the internal model which is saved between updates of the component if 'reset' is false.Network oSL
OnOnSwitch Off to not calculate anything.Boolean
SettingsSettingsSettings for the Learning processRPROP Learning Settings

Outputs

NameIDDescriptionType
NetworkNetworkTrained NetworkNetwork oSL
ErrErrError rates during the history of Learning StepsNumber
HistHistHistory of Networks during LearningNetwork oSL
IterIterIteration CountInteger
TimeTimeTotal time spent on learning in millisecondsNumber

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