健身功能训练 [英] Training on a fitness function

问题描述

我正在查看 FANN (快速人工神经网络)来创建一个神经网络来驱动模拟中的轨道周围的汽车.

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

可以在固定的数据集上进行训练，但这不适用于训练汽车驾驶.我想使用健身功能来训练我的神经网络.这可能吗?

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?

是否可以告诉FANN使用适应度函数，而不是使用固定数据集来训练NN?

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

推荐答案

我想使用健身功能来训练我的NN.这可能吗?

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

健身功能判断效率(标记或从生成的数据中选择)；不是网络本身的功能.

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

是否可以告诉FANN使用适应度函数，而不是使用固定数据集来训练NN?

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

fann_train 使用 FANN_TRAIN_INCREMENTAL .

这篇关于健身功能训练的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！