-1

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?

user4157124
  • 2,809
  • 13
  • 27
  • 42
Rocketmagnet
  • 5,656
  • 8
  • 36
  • 47
  • 1
    Does this answer your question? [As new data becomes available, how to incrementally train a FANN?](https://stackoverflow.com/questions/12838431/as-new-data-becomes-available-how-to-incrementally-train-a-fann) – user4157124 Oct 26 '21 at 19:37

1 Answers1

0

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.

user4157124
  • 2,809
  • 13
  • 27
  • 42