Training on a fitness function

问题:

I am looking at FANN (Fast Artificial Neural Network) to create a neural network to drive a car around a track in a simulation.

It's possible to train on a fixed data set, but this isn't suitable for training a car to drive. I would like to use a fitness function to train my NN. Is this possible?

Is it possible to tell FANN to use a fitness function rather than a fixed data set to train a NN?

回答1:

I would like to use a fitness function to train my NN. Is this possible?

Fitness functions judge efficiency (to label- or select from generated data); not a function of the network itself.

Is it possible to tell FANN to use a fitness function rather than a fixed data set to train a NN?

fann_train adjusts weights per individual set using FANN_TRAIN_INCREMENTAL.