what does the weight_loss mean in loss function?

[ZhouJiaHuan]

[contactmat85]

I didn't understand it neither

[mangwaier]

  weight_decay = tf.multiply(tf.nn.l2_loss(var), wd, name='weight_loss')
  tf.add_to_collection('losses', weight_decay)

As the code say, there is a weight decay based on L2.