Over the next few years, the relative weights of all these policies will change.

在接下来的几年，所有政策的相对权重会发生变化。

The network then learns to classify those samples by adjusting the relative weights assigned to particular features.

然后，网络通过调整分配给特定特征的相对权重来学习对这些样本进行分类。

These three values are summed together, with different relative weights, to produce a controller output that’s passed to the system.

这三个值以不同的相对权重加在一起，以产生传递给系统的控制器输出。