Sets allowed activations for evolution, a random activation method will be chosen from the array when activation mutation occurs.
If set to true, will clear the network after every activation. This is useful for evolving recurrent networks, more importantly for time series prediction.
A set of input values and ideal output values to evaluate a genome's fitness with. Must be included to use NEAT.evaluate without passing a dataset.
Elitism of every evolution loop. Elitism in genetic algorithms.
If set to true when Network.crossOver runs it will assume both genomes are equally fit.
Set the target error. The algorithm will stop once this target error has been reached.
A fitness function to evaluate the networks. Takes a genome, i.e. a network, and a dataset and sets the genome's score property
Num of generations already done.
The input size of the network.
Set the maximum amount of iterations/generations for the algorithm to run.
If set to n, outputs training status every n iterations. Setting log to 1 will log the status every iteration
Specify the loss function for the evolution, this tells a genome in the population how well it's performing. Default: methods.loss.MSE (recommended).
Maximum connections for a potential network
Maximum gates for a potential network
Maximum nodes for a potential network
If mutation occurs (randomNumber < mutationRate), sets amount of times a mutation method will be applied to the network.
Sets the mutation rate. If set to 0.3, 30% of the new population will be mutated.
Sets allowed mutation methods for evolution, a random mutation method will be chosen from the array when mutation occurs. Optional, but default methods are non-recurrent.
The output size of the network.
Population size of each generation.
You can schedule tasks to happen every n iterations. Paired with options.schedule.function
Selection method for evolution (e.g. methods.Selection.FITNESSPROPORTIONATE).
A template network to create the population from.
Train options used for training in between two evolution steps
Generated using TypeDoc
Options used to evolve network