Package paramstores contains the implementation of all the supported storage adapters for the network parameters.

DerivedF is the derivative of the bipolar sigmoid.

F is the bipolar sigmoid function.

ID2Type takes a string and attempts to extract a net ID from it, when it comes to errors there can be false negatives but not false positives (no error doesn't necessarily mean it's a good ID).

List encapsulates the logic required to fill in BriefNet objects from the IDs of nets in the store.

LoadNetwork is used to retrieve network params for a given ID and build a network object with them.

MLPFromParams returns a multilayer perceptron network initialized with the specified params.

MLPTopology returns an array of neurons per layer given the number of inputs, outputs and hidden layers.

NewMLP returns a multilayer perceptron net built from scratch with the requested inputs, outputs and hidden layers.

NewNetwork returns an initialized neural network of the type specified in the configuration.

NewPopulation creates a new set of individuals and initializes their metadata.

Required returns the number of patterns required to train a net (of the most demanding type) with the specified topology.

Trainer listens for requests to train neural nets with new points.

Chromosome represents a neural network configuration.

MLP holds the neurons and thus serves to keep track of the values through the network during training and operation.

Neuron holds the state of the smallest component in a neural net.

Population represents a collection of individuals and their metadata.

Network represents the neural net implementation that is being used.