++ed by:
NGLENN SALVA POTATOGIM

3 PAUSE users
2 non-PAUSE users.

Rutger Vos
and 1 contributors

NAME

AI::FANN::Evolving - artificial neural network that evolves

METHODS

new

Constructor requires 'file', or 'data' and 'neurons' arguments. Optionally takes 'connection_rate' argument for sparse topologies. Returns a subclass of AI::FANN.

clone

Clones the ANN by serializing it to a temporary file and creating a new instance from that file

train

Trains the AI on the provided data object

continuous_properties

Returns a list of names for the AI::FANN properties that are continuous valued and that can be mutated

discrete_properties

Returns a list of names for the AI::FANN properties that are discrete valued and that can be mutated

error

Getter/setter for the error rate. Default is 0.0001

epochs

Getter/setter for the number of training epochs, default is 500000

epoch_printfreq

Getter/setter for the number of epochs after which progress is printed. default is 1000

neurons

Getter/setter for the number of neurons. Default is 15

neuron_printfreq

Getter/setter for the number of cascading neurons after which progress is printed. default is 10

train_type

Getter/setter for the training type: 'cascade' or 'ordinary'. Default is ordinary

activation_function

Getter/setter for the function that maps inputs to outputs. default is FANN_SIGMOID_SYMMETRIC